Paper Digest: Recent Papers on Style Transfer
Paper Digest Team extracted all recent Style Transfer related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
This curated list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that gets you the personalized and comprehensive daily paper digests on the latest research in your field. It also empowers you to read articles, write articles, get answers, conduct literature reviews and generate research reports.
Experience the full potential of our services today!
TABLE 1: Paper Digest: Recent Papers on Style Transfer
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Edit Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We collected and filtered high quality data of limited specific styles and synthesized triplets with thousands categories of style images in-the-wild. We introduce the Curriculum Continual Learning framework to train QwenStyle with such mixture of clean and noisy triplets, which enables QwenStyle to generalize to unseen styles without degradation of the precise content preservation capability. |
Shiwen Zhang; Haibin Huang; Chi Zhang; Xuelong Li; | arxiv-cs.CV | 2026-01-08 |
| 2 | FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, their facial details, structures and identity may not be consistent with the input. In this paper, we address this issue by proposing a style transfer-based facial texture refinement method named FaceRefiner. |
CHENGYANG LI et. al. | arxiv-cs.CV | 2026-01-07 |
| 3 | LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these, we propose LAMS-Edit, leveraging intermediate states from the inversion process–an essential step in real-image editing–during edited image generation. |
Wingwa Fu; Takayuki Okatani; | arxiv-cs.CV | 2026-01-06 |
| 4 | Stroke Patches: Customizable Artistic Image Styling Using Regression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel, regression-based method for artistically styling images. |
Ian Jaffray; John Bronskill; | arxiv-cs.GR | 2026-01-06 |
| 5 | DreamStyle: A Unified Framework for Video Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Additionally, their lack of high-quality datasets leads to style inconsistency and temporal flicker. To address these limitations, we introduce DreamStyle, a unified framework for video stylization, supporting (1) text-guided, (2) style-image-guided, and (3) first-frame-guided video stylization, accompanied by a well-designed data curation pipeline to acquire high-quality paired video data. |
MENGTIAN LI et. al. | arxiv-cs.CV | 2026-01-06 |
| 6 | Deep Learning-based Painting Style Migration Algorithm and Its Visualization and Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study focuses on deep learning-based painting style transfer algorithms. |
Jiayin Liu; | WSEAS TRANSACTIONS ON COMPUTER RESEARCH | 2026-01-05 |
| 7 | IntraStyler: Exemplar-based Style Synthesis for Cross-modality Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an exemplar-based style synthesis method named IntraStyler, which can capture diverse intra-domain styles without any prior knowledge. |
HAN LIU et. al. | arxiv-cs.CV | 2026-01-01 |
| 8 | DynaDrag: Dynamic Drag-Style Image Editing By Motion Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Other methods under different frameworks suffer from various problems like the huge gap between source image and target edited image as well as unreasonable intermediate point which can lead to low editability. To avoid these problems, we propose DynaDrag, the first dragging method under predict-and-move framework. |
Jiacheng Sui; Yujie Zhou; Li Niu; | arxiv-cs.CV | 2026-01-01 |
| 9 | Research and Analysis of Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper provides a systematic and comprehensive overview of the development of image style transfer technology, thoroughly reviewing the technical evolution from early optimization-based methods to modern deep learning frameworks. |
Jingyang Li; | Applied and Computational Engineering | 2025-12-31 |
| 10 | Comparative Evaluation of CNN Architectures for Neural Style Transfer in Indonesian Batik Motif Generation: A Comprehensive Study Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study presents a systematic comparative analysis of five widely used CNN backbones, namely VGG16, VGG19, Inception V3, ResNet50, and ResNet101, based on 245 controlled experiments combining quantitative metrics, qualitative assessment, and statistical analysis to examine the trade-off between structural preservation, stylistic behavior, and computational efficiency. |
Happy Gery Pangestu; Andi Prademon Yunus; Siti Khomsah; | arxiv-cs.CV | 2025-12-31 |
| 11 | Deterministic Image-to-Image Translation Via Denoising Brownian Bridge Models with Dual Approximators Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a denoising Brownian bridge model with dual approximators (Dual-approx Bridge), a novel generative model that exploits the Brownian bridge dynamics and two neural network-based approximators (one for forward and one for reverse process) to produce faithful output with negligible variance and high image quality in I2I translations. |
Bohan Xiao; Peiyong Wang; Qisheng He; Ming Dong; | arxiv-cs.CV | 2025-12-29 |
| 12 | Application of Multimodal Fusion Generative Adversarial Networks in Cross-domain Artistic Style Conversion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Leveraging advanced Generative Adversarial Networks (GAN) architectures, this research aims to improve cross-domain style transfer by integrating multimodal fusion techniques. |
Yongnian Sha; | Discover Artificial Intelligence | 2025-12-24 |
| 13 | UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose UTDesign, a unified framework for high-precision stylized text editing and conditional text generation in design images, supporting both English and Chinese scripts. |
YIMING ZHAO et. al. | arxiv-cs.CV | 2025-12-23 |
| 14 | Generative Latent Coding for Ultra-Low Bitrate Image Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they encounter difficulties in achieving both high-realism and high-fidelity at low bitrate, as the pixel-space distortion may not align with human perception. To address this issue, we introduce a Generative Latent Coding (GLC) architecture, which performs transform coding in the latent space of a generative vector-quantized variational auto-encoder (VQ-VAE), instead of in the pixel space. |
Zhaoyang Jia; Jiahao Li; Bin Li; Houqiang Li; Yan Lu; | arxiv-cs.CV | 2025-12-23 |
| 15 | Uni-Neur2Img: Unified Neural Signal-Guided Image Generation, Editing, and Stylization Via Diffusion Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, We present Uni-Neur2Img, a unified framework for neural signal-driven image generation and editing. |
XIYUE BAI et. al. | arxiv-cs.CV | 2025-12-21 |
| 16 | LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a training- and inference-light, interpretable method for representing and transferring artistic style. |
RAINA PANDA et. al. | arxiv-cs.CV | 2025-12-21 |
| 17 | Plasticine: A Traceable Diffusion Model for Medical Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This property enhances clinical interpretability but has been largely overlooked in previous approaches. To address this gap, we propose Plasticine, which is, to the best of our knowledge, the first end-to-end image-to-image translation framework explicitly designed with traceability as a core objective. |
TIANYANG ZHANNG et. al. | arxiv-cs.CV | 2025-12-20 |
| 18 | Loom: Diffusion-Transformer for Interleaved Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Loom, a unified diffusion-transformer framework for interleaved text-image generation. |
Mingcheng Ye; Jiaming Liu; Yiren Song; | arxiv-cs.CV | 2025-12-20 |
| 19 | All-optical Synthesis Chip for Large-scale Intelligent Semantic Vision Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Large-scale generative artificial intelligence (AI) is facing a severe computing power shortage. Although photonic computing achieves excellence in decision tasks, its application … |
YITONG CHEN et. al. | Science | 2025-12-18 |
| 20 | Stylized Synthetic Augmentation Further Improves Corruption Robustness Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models to common corruptions. |
GEORG SIEDEL et. al. | arxiv-cs.CV | 2025-12-17 |
| 21 | SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SCAdapter, a novel technique leveraging CLIP image space to effectively separate and integrate content and style features. |
Luan Thanh Trinh; Kenji Doi; Atsuki Osanai; | arxiv-cs.CV | 2025-12-14 |
| 22 | Two-Step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a two-step generative data augmentation framework that combines rule-based mask warping with unpaired image-to-image translation using GANs, enabling the generation of realistic masked-face samples beyond purely synthetic transformations. |
Yan Yang; George Bebis; Mircea Nicolescu; | arxiv-cs.CV | 2025-12-13 |
| 23 | EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the global denoising dynamics of DMs inherently conflate local editing targets with the full-image context, leading to unintended modifications in non-target regions. In this paper, we shift our attention beyond DMs and turn to Masked Generative Transformers (MGTs) as an alternative approach to tackle this challenge. |
WEI CHOW et. al. | arxiv-cs.CV | 2025-12-12 |
| 24 | Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we adapt the Inversion-Based Style Transfer (InST) framework originally designed for artistic style transfer to biomedical microscopy images. |
Mohammad Dehghanmanshadi; Wallapak Tavanapong; | arxiv-cs.CV | 2025-12-12 |
| 25 | Preserving Photographic Defocus in Stylised Image Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Abstract While style transfer has been extensively studied, most existing approaches fail to account for the defocus effects inherent in content images, thereby compromising the photographer’s intended focus cues. To overcome this shortcoming, we introduce an optimisation‐based post‐processing framework that restores defocus characteristics to stylised images, regardless of the style transfer technique used. |
Hong‐Yi Wang; Yu‐Ting Wu; | Computer Graphics Forum | 2025-12-10 |
| 26 | DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization Via Disentangled Anatomy-Contrast Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: When applied to imaging data, image-based harmonization approaches are often restricted by the need for target images, while existing text-guided methods rely on simplistic labels that fail to capture complex acquisition details or are typically restricted to datasets with limited variability, failing to capture the heterogeneity of real-world clinical environments. To address these limitations, we propose DIST-CLIP (Disentangled Style Transfer with CLIP Guidance), a unified framework for MRI harmonization that flexibly uses either target images or DICOM metadata for guidance. |
MEHMET YIGIT AVCI et. al. | arxiv-cs.CV | 2025-12-08 |
| 27 | EmoStyle: Emotion-Driven Image Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present EmoStyle, a framework designed to address key challenges in AIS, including the lack of training data and the emotion-style mapping. |
Jingyuan Yang; Zihuan Bai; Hui Huang; | arxiv-cs.CV | 2025-12-05 |
| 28 | Adaptation Art Image Style Transfer By Integrating CSDA-FD Algorithm and OSDA-DS Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The transfer process can easily lead to a decrease in training set performance, affecting the effectiveness of transfer learning. Therefore, this study proposes a domain adaptation model that combines feature disentangling and disentangling subspaces. |
Peng Wang; | Machine Graphics & Vision | 2025-12-04 |
| 29 | NeuralRemaster: Phase-Preserving Diffusion for Structure-Aligned Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Phase-Preserving Diffusion φ-PD, a model-agnostic reformulation of the diffusion process that preserves input phase while randomizing magnitude, enabling structure-aligned generation without architectural changes or additional parameters. |
YU ZENG et. al. | arxiv-cs.CV | 2025-12-04 |
| 30 | One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfe Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Handling reference-pose misalignment remains unsolved. To address this, we present One-to-All Animation, a unified framework for high-fidelity character animation and image pose transfer for references with arbitrary layouts. |
SHIJUN SHI et. al. | arxiv-cs.CV | 2025-11-28 |
| 31 | Low-Resolution Editing Is All You Need for High-Resolution Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce the task of high-resolution image editing and propose a test-time optimization framework to address it. |
Junsung Lee; Hyunsoo Lee; Yong Jae Lee; Bohyung Han; | arxiv-cs.CV | 2025-11-25 |
| 32 | TReFT: Taming Rectified Flow Models For One-Step Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although the recent adversarial training paradigm, CycleGAN-Turbo, works in pretrained diffusion models for one-step image translation, we find that directly applying it to RF models leads to severe convergence issues. In this paper, we analyze these challenges and propose TReFT, a novel method to Tame Rectified Flow models for one-step image Translation. |
SHENGQIAN LI et. al. | arxiv-cs.CV | 2025-11-25 |
| 33 | IMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. |
ZHOUJIE FU et. al. | arxiv-cs.CV | 2025-11-25 |
| 34 | Inversion-Free Style Transfer with Dual Rectified Flows Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While mainstream training-free diffusion-based methods have greatly advanced style transfer in recent years, their reliance on computationally inversion processes compromises efficiency and introduces visual distortions when inversion is inaccurate. To address these limitations, we propose a novel \textit{inversion-free} style transfer framework based on dual rectified flows, which tackles the challenge of finding an unknown stylized distribution from two distinct inputs (content and style images), \textit{only with forward pass}. |
Yingying Deng; Xiangyu He; Fan Tang; Weiming Dong; Xucheng Yin; | arxiv-cs.CV | 2025-11-25 |
| 35 | MimiCAT: Mimic with Correspondence-Aware Cascade-Transformer for Category-Free 3D Pose Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: 3D pose transfer aims to transfer the pose-style of a source mesh to a target character while preserving both the target’s geometry and the source’s pose characteristic. Existing … |
Zenghao Chai; Chen Tang; Yongkang Wong; Xulei Yang; Mohan Kankanhalli; | arxiv-cs.CV | 2025-11-23 |
| 36 | UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using A Frozen Black-Box Inference Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing UIT approaches often overlook class-specific semantic alignment during domain adaptation, resulting in misaligned content-class mappings that can impair diagnostic accuracy. To address this limitation, we propose UI-Styler, a novel ultrasound-specific, class-aware image style transfer framework. |
Nhat-Tuong Do-Tran; Ngoc-Hoang-Lam Le; Ching-Chun Huang; | arxiv-cs.CV | 2025-11-21 |
| 37 | Show Me: Unifying Instructional Image and Video Generation with Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose ShowMe, a unified framework that enables both tasks by selectively activating the spatial and temporal components of video diffusion models. |
Yujiang Pu; Zhanbo Huang; Vishnu Boddeti; Yu Kong; | arxiv-cs.CV | 2025-11-21 |
| 38 | ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing image manipulation detection and localization (IMDL) benchmarks suffer from limited content diversity, narrow generative-model coverage, and insufficient interpretability, which hinders the generalization and explanation capabilities of current manipulation detection methods. To address these limitations, we introduce \textbf{ManipBench}, a large-scale benchmark for image manipulation detection and localization focusing on AI-edited images. |
ZITONG XU et. al. | arxiv-cs.CV | 2025-11-18 |
| 39 | AnoStyler: Text-Driven Localized Anomaly Generation Via Lightweight Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods typically sufferfrom at least one of the following limitations, hindering their practicaldeployment: (1) lack of visual realism in generated anomalies; (2) dependenceon large amounts of real images; and (3) use of memory-intensive, heavyweightmodel architectures. To overcome these limitations, we propose AnoStyler, alightweight yet effective method that frames zero-shot anomaly generation astext-guided style transfer. |
Yulim So; Seokho Kang; | arxiv-cs.CV | 2025-11-09 |
| 40 | V-Shuffle: Zero-Shot Style Transfer Via Value Shuffle Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose V-Shuffle, a zero-shot styletransfer method that leverages multiple style images from the same style domainto effectively navigate the trade-off between content preservation and stylefidelity. |
Haojun Tang; Qiwei Lin; Tongda Xu; Lida Huang; Yan Wang; | arxiv-cs.CV | 2025-11-09 |
| 41 | CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we introduce CLIPGaussian, the first unified style transfer framework that supports text- and image-guided stylization across multiple modalities: 2D images, videos, 3D objects, and 4D scenes. |
KORNEL HOWIL et. al. | nips | 2025-11-07 |
| 42 | Free-Lunch Color-Texture Disentanglement for Stylized Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation, addressing the need for independently controlled style elements for the Disentangled Stylized Image Generation (DisIG) problem. |
JIANG QIN et. al. | nips | 2025-11-07 |
| 43 | OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: GPT-4o’s exceptional stylization consistency highlights the performance gap between open-source methods and proprietary models. To bridge this gap, we propose \textbf{OmniConsistency}, a universal consistency plugin leveraging large-scale Diffusion Transformers (DiTs). |
Yiren Song; Cheng Liu; Mike Zheng Shou; | nips | 2025-11-07 |
| 44 | CSGO: Content-Style Composition in Text-to-Image Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Empowered by IMAGStyle, we propose CSGO, a unified, end-to-end trainable framework that decouples content and style representations via independent feature injection. |
PENG XING et. al. | nips | 2025-11-07 |
| 45 | ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we propose ThermalGen, an adaptive flow-based generative model for RGB-T image translation, incorporating an RGB image conditioning architecture and a style-disentangled mechanism.To support large-scale training, we curated eight public satellite-aerial, aerial, and ground RGB-T paired datasets, and introduced three new large-scale satellite-aerial RGB-T datasets–DJI-day, Bosonplus-day, and Bosonplus-night–captured across diverse times, sensor types, and geographic regions. |
Jiuhong Xiao; Roshan Nayak; Ning Zhang; Daniel Toertei; Giuseppe Loianno; | nips | 2025-11-07 |
| 46 | Color Conditional Generation with Sliced Wasserstein Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SW-Guidance, a training-free approach for image generation conditioned on the color distribution of a reference image. |
Alexander Lobashev; Maria Larchenko; Dmitry Guskov; | nips | 2025-11-07 |
| 47 | AStF: Motion Style Transfer Via Adaptive Statistics Fusor Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Specifically, we propose a novel Adaptive StatisticsFusor (AStF) which consists of Style Disentanglement Module (SDM) andHigh-Order Multi-Statistics Attention (HOS-Attn). |
Hanmo Chen; Chenghao Xu; Jiexi Yan; Cheng Deng; | arxiv-cs.CV | 2025-11-06 |
| 48 | NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In thiswork, we present a novel contrastive learning framework to improve thestylization capability of large text-to-image diffusion models. |
Serkan Ozturk; Samet Hicsonmez; Pinar Duygulu; | arxiv-cs.CV | 2025-11-03 |
| 49 | Training-free Style Transfer Via Content-style Image Inversion Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Songlin Lei; Qiuxia Yang; Ke Yang; Zhengpeng Zhao; Yuanyuan Pu; | Comput. Graph. | 2025-11-01 |
| 50 | GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Precise geometric control in image generation is essential for engineering \&product design and creative industries to control 3D object features accuratelyin image space. … |
PHILLIP MUELLER et. al. | arxiv-cs.CV | 2025-10-25 |
| 51 | UTILIZATION OF AI IN MARKETING CREATIVE PRODUCTS MADE FROM WOOD WASTE IN THE CRAFTSMEN COMMUNITY OF NGEMPLAK DISTRICT, BOYOLALI REGENCY Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study explores the application of Artificial Intelligence (AI) to enhance the aesthetic quality and design innovation of creative products made from wood waste in Ngemplak District, Boyolali Regency, Indonesia. |
Siswanto Siswanto; Nughthoh Arfawi Kurdhi; Nugroho Arif Sudibyo; Supriyadi Wibowo; Putranto Hadi Utomo; | J-ABDI: Jurnal Pengabdian kepada Masyarakat | 2025-10-24 |
| 52 | Real-Time Neural Style Transfer in Game Engines: A Comprehensive Review Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In recent years, the application of NST in real-time scenarios—especially within game engines—has attracted significant academic and industrial interest. This paper provides a comprehensive review of the development of NST from its origins in 2D image transformation to its extension in video, 3D meshes, and real-time rendering. |
Yihan Luo; | Science and Technology of Engineering, Chemistry and … | 2025-10-23 |
| 53 | Intelligent Interior Decoration Style Recommendation and Customization System Based on Deep Learning Style Transfer Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a system framework for the intelligent recommendation and customization of interior decoration styles based on the deep learning style transfer algorithm. |
Yang Li; | Journal of Computational Methods in Sciences and Engineering | 2025-10-21 |
| 54 | Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, when the scene is rendered from novel camera views, particularly in unseen regions far away from the input camera, existing single image to 3D reconstruction methods render incoherent and blurry views. In this work, we address these inherent limitations in existing single image-to-3D scene feedforward networks. |
SAROSIJ BOSE et. al. | iccv | 2025-10-20 |
| 55 | Co-Painter: Fine-Grained Controllable Image Stylization Via Implicit Decoupling and Adaptive Injection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods often treat the style in the reference image as a single, indivisible entity, which makes it difficult to transfer specific stylistic attributes. To address this issue, we propose a fine-grained controllable image stylization framework, Co-Painter, to decouple multiple attributes embedded in the reference image and adaptively inject it into the diffusion model. |
BOWEN FU et. al. | iccv | 2025-10-20 |
| 56 | GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Traditional 3D editing approaches are time-consuming and demand specialized skills, while current image-based generative methods lack accuracy in geometric conditioning. To address these challenges, we propose GeoDiffusion, a training-free framework for accurate and efficient geometric conditioning of 3D features in image generation. |
PHILLIP MUELLER et. al. | iccv | 2025-10-20 |
| 57 | FlowStyler: Artistic Video Stylization Via Transformation Fields Transports Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While generator-based methods produce visually striking stylized results, they suffer from flickering artifacts in dynamic motion scenarios and require prohibitive computational resources. Conversely, non-generative techniques frequently show either temporal inconsistency or inadequate style preservation.We address these limitations by adapting the physics-inspired transport principles from the Transport-based Neural Style Transfer (TNST) framework (originally developed for volumetric fluid stylization) to enforce inter-frame consistency in video stylization.Our framework employs two complementary transformation fields for artistic stylization: a geometric stylization velocity field governing deformation and an orthogonality-regularized color transfer field managing color adaptations. |
Yuning Gong; Jiaming Chen; Xiaohua Ren; Yuanjun Liao; Yanci Zhang; | iccv | 2025-10-20 |
| 58 | Wasserstein Style Distribution Analysis and Transform for Stylized Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we systematically analyze the relationship between features in attention blocks and style. |
Xi Yu; Xiang Gu; Zhihao Shi; Jian Sun; | iccv | 2025-10-20 |
| 59 | TextMaster: A Unified Framework for Realistic Text Editing Via Glyph-Style Dual-Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods, however, face significant limitations in terms of stroke accuracy for complex text and controllability of generated text styles. To address these challenges, we propose TextMaster, a solution capable of accurately editing text across various scenarios and image regions, while ensuring proper layout and controllable text style. |
ZHENYU YAN et. al. | iccv | 2025-10-20 |
| 60 | Balanced Image Stylization with Style Matching Score Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Style Matching Score (SMS), a novel optimization method for image stylization with diffusion models. |
YUXIN JIANG et. al. | iccv | 2025-10-20 |
| 61 | CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The current conditional autoregressive image generation methods have shown promising results, yet their potential remains largely unexplored in the practical unsupervised image translation domain, which operates without explicit cross-domain correspondences.A critical limitation stems from the discrete quantization inherent in traditional Vector Quantization-based frameworks, which disrupts gradient flow between the Variational Autoencoder decoder and causal Transformer, impeding end-to-end optimization during adversarial training in image space.To tackle this issue, we propose using Softmax Relaxed Quantization, a novel approach that reformulates codebook selection as a continuous probability mixing process via Softmax, thereby preserving gradient propagation. |
Yi Liu; Shengqian Li; Zuzeng Lin; Feng Wang; Si Liu; | iccv | 2025-10-20 |
| 62 | Domain Generalizable Portrait Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a portrait style transfer method that generalizes well to various different domains while enabling high-quality semantic-aligned stylization on regions including hair, eyes, eyelashes, skins, lips, and background. |
Xinbo Wang; Wenju Xu; Qing Zhang; Wei-Shi Zheng; | iccv | 2025-10-20 |
| 63 | Frequency-Guided Diffusion for Training-Free Text-Driven Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on the observation that the low-/high-frequency components retain style/structure information of image, in this work, we propose training-free Frequency-Guided Diffusion (FGD), which tailors low-/high-frequency guidance for style- and structure-guided translation, respectively. |
Zheng Gao; Jifei Song; Zhensong Zhang; Jiankang Deng; Ioannis Patras; | iccv | 2025-10-20 |
| 64 | SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Photorealistic style transfer (PST) enables real-world color grading by adapting reference image colors while preserving content structure.Existing methods mainly follow either approaches: generation-based methods that prioritize stylistic fidelity at the cost of content integrity and efficiency, or global color transformation methods such as LUT, which preserve structure but lack local adaptability. To bridge this gap, we propose Spatial Adaptive 4D Look-Up Table (SA-LUT), combining LUT efficiency with neural network adaptability. |
Zerui Gong; Zhonghua Wu; Qingyi Tao; Qinyue Li; Chen Change Loy; | iccv | 2025-10-20 |
| 65 | A Hybrid Conditional GAN Design for Image-to-Image Translation Integrating U-Net and ResNet Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study introduces a novel approach for image-to-image translation based on a conditional generator adversarial network with a new hybrid generator architecture that combines the U-Net and ResNet architectures. |
Khaled Al Hariri; Muhammet Paşaoğlu; Erkut Arıcan; | Firat University Journal of Experimental and Computational … | 2025-10-20 |
| 66 | IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although existing methods have advanced the field, their reliance on synthetic infrared images generated through style transfer from visible images, which limits their ability to capture the unique characteristics of the infrared modality. To address this, we propose IRGPT, the first multi-modal large language model for real-world infrared images, built upon a large-scale InfraRed-Text Dataset (IR-TD) comprising over 260K authentic image-text pairs. |
Zhe Cao; Jin Zhang; Ruiheng Zhang; | iccv | 2025-10-20 |
| 67 | AnyI2V: Animating Any Conditional Image with Motion Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although some methods incorporate ControlNet to introduce image-based conditioning, they often lack explicit motion control and require computationally expensive training. To address these limitations, we propose AnyI2V, a training-free framework that animates any conditional images with user-defined motion trajectories. |
Ziye Li; Hao Luo; Xincheng Shuai; Henghui Ding; | iccv | 2025-10-20 |
| 68 | Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a creative intensity-tunable 3D style transfer paradigm, dubbed Tune-Your-Style, which allows users to flexibly adjust the style intensity injected into the scene to match their desired content-style balance, thus enhancing the customizability of 3D style transfer. |
YIAN ZHAO et. al. | iccv | 2025-10-20 |
| 69 | A3GS: Arbitrary Artistic Style Into Arbitrary 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose A^3GS, a novel feed-forward neural network for zero-shot 3DGS stylization that enables transferring any image style to arbitrary 3D scenes in just 10 seconds without the need for per-style optimization. |
ZHIYUAN FANG et. al. | iccv | 2025-10-20 |
| 70 | LBM: Latent Bridge Matching for Fast Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation. |
Clément Chadebec; Onur Tasar; Sanjeev Sreetharan; Benjamin Aubin; | iccv | 2025-10-20 |
| 71 | Holistic Tokenizer for Autoregressive Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, because most visual tokenizers map local image patches into latent tokens, global information is limited. To address this, we introduce Hita, a novel image tokenizer for autoregressive (AR) image generation. |
ANLIN ZHENG et. al. | iccv | 2025-10-20 |
| 72 | Style Transfer from Sentinel-1 to Sentinel-2 for Fluvial Scenes with Multi-Modal and Multi-Temporal Image Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we develop a solution to the use of Sentinel-1 radar images for the semantic classification of water bodies that uses style transfer with multi-modal and multi-temporal image fusion. |
Patrice E. Carbonneau; | Remote Sensing | 2025-10-15 |
| 73 | Design of Personalized Creation Model for Cultural and Creative Products Based on Evolutionary Adaptive Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Addressing the limitations of current generative models—particularly in maintaining stylistic coherence and accommodating individualized preferences—this article introduces a novel image synthesis framework grounded in a synergistic mechanism that integrates text-driven guidance, adaptive style modulation, and evolutionary optimization: Evolutionary Adaptive Generative Aesthetic Network (EAGAN). |
Dailei Hu; Enshi Wang; Muddassira Arshad; | PeerJ Computer Science | 2025-10-14 |
| 74 | Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces a method to utilize data from unlabeled domains to trainControlNets by introducing the concept of uncertainty into the controlmechanism. |
Joshua Niemeijer; Jan Ehrhardt; Heinz Handels; Hristina Uzunova; | arxiv-cs.CV | 2025-10-13 |
| 75 | Jigsaw3D: Disentangled 3D Style Transfer Via Patch Shuffling and Masking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our key idea is toleverage the jigsaw operation – spatial shuffling and random masking ofreference patches – to suppress object semantics and isolate stylisticstatistics (color palettes, strokes, textures). |
YUTENG YE et. al. | arxiv-cs.CV | 2025-10-12 |
| 76 | Training-Free In-Context Forensic Chain for Image Manipulation Detection and Localization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose the In-Context Forensic Chain (ICFC), atraining-free framework that leverages multi-modal large language models(MLLMs) for interpretable IML tasks. |
RUI CHEN et. al. | arxiv-cs.CV | 2025-10-11 |
| 77 | StyleMM: Stylized 3D Morphable Face Model Via Text‐Driven Aligned Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Abstract We introduce StyleMM, a novel framework that can construct a stylized 3D Morphable Model (3DMM) based on user‐defined text descriptions specifying a target style. |
Seungmi Lee; Kwan Yun; Junyong Noh; | Computer Graphics Forum | 2025-10-11 |
| 78 | ReMix: Towards A Unified View of Consistent Character Generation and Editing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1)have greatly improved visual fidelity in consistent character generation andediting. However, existing … |
BENJIA ZHOU et. al. | arxiv-cs.CV | 2025-10-11 |
| 79 | Lesion-Aware Post-Training of Latent Diffusion Models for Synthesizing Diffusion MRI from CT Perfusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Failure to accurately reconstructthese regions can severely impact diagnostic reliability and clinicaldecision-making. To overcome this limitation, we propose a novel post-trainingframework for LDMs in medical image-to-image translation by incorporatinglesion-aware medical pixel space objectives. |
JUNHYEOK LEE et. al. | arxiv-cs.CV | 2025-10-10 |
| 80 | UniVideo: Unified Understanding, Generation, and Editing for Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In thiswork, we present UniVideo, a versatile framework that extends unified modelingto the video domain. |
CONG WEI et. al. | arxiv-cs.CV | 2025-10-09 |
| 81 | PickStyle: Video-to-Video Style Transfer with Context-Style Adapters Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose PickStyle, a video-to-video styletransfer framework that augments pretrained video diffusion backbones withstyle adapters and benefits from paired still image data with source-stylecorrespondences for training. |
Soroush Mehraban; Vida Adeli; Jacob Rommann; Babak Taati; Kyryl Truskovskyi; | arxiv-cs.CV | 2025-10-08 |
| 82 | PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce PyramidStyler, a transformer frameworkwith Pyramidal Positional Encoding (PPE): a hierarchical, multi-scale encodingthat captures both local details and global context while reducingcomputational load. |
Raahul Krishna Durairaju; K. Saruladha; | arxiv-cs.CV | 2025-10-02 |
| 83 | FreeViS: Training-free Video Stylization with Inconsistent References Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose FreeViS, a training-freevideo stylization framework that generates stylized videos with rich styledetails and strong temporal coherence. |
Jiacong Xu; Yiqun Mei; Ke Zhang; Vishal M. Patel; | arxiv-cs.CV | 2025-10-02 |
| 84 | MSHRT-Net: Multi-scale Hierarchical Residual Transfer Network for Image Manipulation Detection and Localization Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Xiao Yang; Xiu-li Chai; Zhihua Gan; Lvchen Cao; Yushu Zhang; | Neurocomputing | 2025-10-01 |
| 85 | Multi-level Dynamic Style Transfer for NeRFs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we presentmulti-level dynamic style transfer for NeRFs (MDS-NeRF), a novel approach thatreengineers the NeRF pipeline specifically for stylization and incorporates aninnovative dynamic style injection module. |
Zesheng Li; Shuaibo Li; Wei Ma; Jianwei Guo; Hongbin Zha; | arxiv-cs.CV | 2025-10-01 |
| 86 | Editable Noise Map Inversion: Encoding Target-image Into Noise For High-Fidelity Image Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The limitation arises because inverted noise maps, whileenabling faithful reconstruction of the source image, restrict the flexibilityneeded for desired edits. To overcome this issue, we propose Editable Noise MapInversion (ENM Inversion), a novel inversion technique that searches foroptimal noise maps to ensure both content preservation and editability. |
Mingyu Kang; Yong Suk Choi; | arxiv-cs.CV | 2025-09-30 |
| 87 | Bézier Meets Diffusion: Robust Generation Across Domains for Medical Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a unified framework, B\’ezier MeetsDiffusion, for cross-domain image generation. |
Chen Li; Meilong Xu; Xiaoling Hu; Weimin Lyu; Chao Chen; | arxiv-cs.CV | 2025-09-26 |
| 88 | One-shot Embroidery Customization Via Contrastive LoRA Modulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Embroidery is a textile art form characterizedby intricate interplay of diverse stitch patterns and material properties,which poses unique challenges for existing style transfer methods. To explorethe customization for such fine-grained features, we propose a novelcontrastive learning framework that disentangles fine-grained style and contentfeatures with a single reference image, building on the classic concept ofimage analogy. |
JUN MA et. al. | arxiv-cs.GR | 2025-09-23 |
| 89 | RaceGAN: A Framework for Preserving Individuality While Converting Racial Information for Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our study aims totranslate racial traits by means of multi-domain image-to-image translation. |
Mst Tasnim Pervin; George Bebis; Fang Jiang; Alireza Tavakkoli; | arxiv-cs.CV | 2025-09-18 |
| 90 | MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Weemploy a novel dataset construction pipeline that utilizes two multi-modallarge language models (MLLMs) to generate visual-adaptive editing instructionsand produce high-fidelity edited images, respectively. |
MINGSONG LI et. al. | arxiv-cs.CV | 2025-09-18 |
| 91 | LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Diffusion models excel at generating high-quality outputs but face challengesin data-scarce domains, where exhaustive retraining or costly paired data areoften required. To address these limitations, we propose Latent AlignedDiffusion Bridges (LADB), a semi-supervised framework for sample-to-sampletranslation that effectively bridges domain gaps using partially paired data.By aligning source and target distributions within a shared latent space, LADBseamlessly integrates pretrained source-domain diffusion models with atarget-domain Latent Aligned Diffusion Model (LADM), trained on partiallypaired latent representations. |
XUQIN WANG et. al. | arxiv-cs.CV | 2025-09-10 |
| 92 | SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While existing methods can transfer style patterns onto3D-consistent neural representations, they struggle to effectively extract andtransfer high-level style semantics from the reference style image.Additionally, the stylized results often lack structural clarity andseparation, making it difficult to distinguish between different instances orobjects within the 3D scene. To address these limitations, we propose a novel3D style transfer pipeline that effectively integrates prior knowledge frompretrained 2D diffusion models. |
JIMIN XU et. al. | arxiv-cs.CV | 2025-09-04 |
| 93 | SMooGPT: Stylized Motion Generation Using Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In thispaper, we propose to solve the stylized motion generation problem from a newperspective of reasoning-composition-generation, based on our observations: i)human motion can often be effectively described using natural language in abody-part centric manner, ii) LLMs exhibit a strong ability to understand andreason about human motion, and iii) human motion has an inherentlycompositional nature, facilitating the new motion content or style generationvia effective recomposing. |
Lei Zhong; Yi Yang; Changjian Li; | arxiv-cs.GR | 2025-09-04 |
| 94 | Improved 3D Scene Stylization Via Text-Guided Generative Image Editing with Region-Based Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address these limitations, weintroduce techniques that enhance the quality of 3D stylization whilemaintaining view consistency and providing optional region-controlled styletransfer. Our method achieves stylization by re-training an initial 3Drepresentation using stylized multi-view 2D images of the source views.Therefore, ensuring both style consistency and view consistency of stylizedmulti-view images is crucial. |
Haruo Fujiwara; Yusuke Mukuta; Tatsuya Harada; | arxiv-cs.GR | 2025-09-04 |
| 95 | Neural Scene Designer: Self-Styled Semantic Image Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce the Neural Scene Designer (NSD), anovel framework that enables photo-realistic manipulation of user-specifiedscene regions while ensuring both semantic alignment with user intent andstylistic consistency with the surrounding environment. |
JIANMAN LIN et. al. | arxiv-cs.CV | 2025-09-01 |
| 96 | Toward Real-Time G-Buffer-Guided Style Transfer in Computer Games Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Artistic neural style transfer (NST) has achieved remarkable success for images. However, this is not the case for dynamic 3-D environments, such as computer games, where temporal … |
E. Ioannou; Steve Maddock; | IEEE Transactions on Games | 2025-09-01 |
| 97 | TRUST: Token-dRiven Ultrasound Style Transfer for Cross-Device Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose TRUST, atoken-driven dual-stream framework that preserves source content whiletransferring the common style of the target domain, ensuring that content andstyle remain unblended. |
Nhat-Tuong Do-Tran; Ngoc-Hoang-Lam Le; Ian Chiu; Po-Tsun Paul Kuo; Ching-Chun Huang; | arxiv-cs.CV | 2025-08-30 |
| 98 | CraftGraffiti: Exploring Human Identity with Custom Graffiti Art Via Facial-Preserving Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: CraftGraffiti advances the goal ofidentity-respectful AI-assisted artistry, offering a principled approach forblending stylistic freedom with recognizability in creative AI applications. |
Ayan Banerjee; Fernando Vilariño; Josep Lladós; | arxiv-cs.CV | 2025-08-28 |
| 99 | PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose anovel framework, PersonaAnimator, which learns personalized motion patternsdirectly from unconstrained videos. |
ZIYUN QIAN et. al. | arxiv-cs.CV | 2025-08-27 |
| 100 | Style4D-Bench: A Benchmark Suite for 4D Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To establish a strong baseline, we present Style4D, anovel framework built upon 4D Gaussian Splatting. |
BEIQI CHEN et. al. | arxiv-cs.CV | 2025-08-26 |
| 101 | Styleclone: Face Stylization with Diffusion Based Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present StyleClone, a method for training image-to-image translationnetworks to stylize faces in a specific style, even with limited style images.Our approach leverages textual inversion and diffusion-based guided imagegeneration to augment small style datasets. |
Neeraj Matiyali; Siddharth Srivastava; Gaurav Sharma; | arxiv-cs.CV | 2025-08-23 |
| 102 | MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Mesh models have become increasingly accessible for numerous cities; however,the lack of realistic textures restricts their application in virtual urbannavigation and autonomous driving. To address this, this paper proposes MeSS(Meshbased Scene Synthesis) for generating high-quality, styleconsistentoutdoor scenes with city mesh models serving as the geometric prior. |
XUYANG CHEN et. al. | arxiv-cs.CV | 2025-08-20 |
| 103 | Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Key challengesinclude generating novel view content that remains consistent with the originalvideo, preserving unedited regions, and translating sparse 2D inputs intorealistic 3D video outputs. To address these issues, we propose Sketch3DVE, asketch-based 3D-aware video editing method to enable detailed localmanipulation of videos with significant viewpoint changes. |
Feng-Lin Liu; Shi-Yang Li; Yan-Pei Cao; Hongbo Fu; Lin Gao; | arxiv-cs.GR | 2025-08-19 |
| 104 | Single-Reference Text-to-Image Manipulation with Dual Contrastive Denoising Score Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by contrastive learning approaches forunpaired image-to-image translation, we introduce a straightforward dualcontrastive loss within the proposed framework. |
Syed Muhmmad Israr; Feng Zhao; | arxiv-cs.CV | 2025-08-18 |
| 105 | Leveraging Diffusion Models for Stylization Using Multiple Style Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, they tend to entanglecontent and style in undesired ways. To address this, we propose leveragingmultiple style images which helps better represent style features and preventcontent leaking from the style images. |
Dan Ruta; Abdelaziz Djelouah; Raphael Ortiz; Christopher Schroers; | arxiv-cs.CV | 2025-08-18 |
| 106 | StyleMM: Stylized 3D Morphable Face Model Via Text-Driven Aligned Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce StyleMM, a novel framework that can construct a stylized 3DMorphable Model (3DMM) based on user-defined text descriptions specifying atarget style. |
Seungmi Lee; Kwan Yun; Junyong Noh; | arxiv-cs.GR | 2025-08-15 |
| 107 | FantasyStyle: Controllable Stylized Distillation for 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current methods stillface two major challenges: (1) multi-view inconsistency often leads to styleconflicts, resulting in appearance smoothing and distortion; and (2) heavyreliance on VGG features, which struggle to disentangle style and content fromstyle images, often causing content leakage and excessive stylization. Totackle these issues, we introduce \textbf{FantasyStyle}, a 3DGS-based styletransfer framework, and the first to rely entirely on diffusion modeldistillation. |
Yitong Yang; Yinglin Wang; Changshuo Wang; Huajie Wang; Shuting He; | arxiv-cs.CV | 2025-08-11 |
| 108 | 3D-Fixup: Advancing Photo Editing with 3D Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite significant advances in modeling image priors via diffusion models, 3D-aware image editing remains challenging, in part because the object is only specified via a single image. To tackle this challenge, we propose 3D-Fixup, a new framework for editing 2D images guided by learned 3D priors. |
YEN-CHI CHENG et. al. | siggraph | 2025-08-10 |
| 109 | GANime: Generating Anime and Manga Character Drawings from Sketches with Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, weexamine multiple models for image-to-image translation between anime charactersand their sketches, including Neural Style Transfer, C-GAN, and CycleGAN. |
Tai Vu; Robert Yang; | arxiv-cs.CV | 2025-08-09 |
| 110 | Optimization-Free Style Transfer for 3D Gaussian Splats Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a reconstruction- and optimization-freeapproach to stylizing 3D Gaussian splats. |
Raphael Du Sablon; David Hart; | arxiv-cs.CV | 2025-08-07 |
| 111 | Improving Masked Style Transfer Using Blended Partial Convolution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a partial-convolution-based style transfer network thataccurately applies the style features exclusively to the region of interest.Additionally, we present network-internal blending techniques that account forimperfections in the region selection. |
Seyed Hadi Seyed; Ayberk Cansever; David Hart; | arxiv-cs.CV | 2025-08-07 |
| 112 | Learning Latent Representations for Image Translation Using Frequency Distributed CycleGAN Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents Fd-CycleGAN, an image-to-image (I2I) translationframework that enhances latent representation learning to approximate real datadistributions. |
Shivangi Nigam; Adarsh Prasad Behera; Shekhar Verma; P. Nagabhushan; | arxiv-cs.CV | 2025-08-05 |
| 113 | StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation overlooksthe semantic gap between the non-spatial nature of textual descriptions and thespatially-aware attributes of visual style, often leading to the loss ofsemantic structure and fine-grained details during stylization. In this paper,we propose StyDeco, an unsupervised framework that resolves this limitation bylearning text representations specifically tailored for the style transfertask. |
YUANLIN YANG et. al. | arxiv-cs.CV | 2025-08-02 |
| 114 | Creative Style Transfer for Image Stylization Via Learning Neural Permutation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
SHIMIN LI et. al. | Knowl. Based Syst. | 2025-08-01 |
| 115 | SIDA: Synthetic Image Driven Zero-shot Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose SIDA, anovel and efficient zero-shot domain adaptation method leveraging syntheticimages. |
Ye-Chan Kim; SeungJu Cha; Si-Woo Kim; Taewhan Kim; Dong-Jin Kim; | arxiv-cs.CV | 2025-07-24 |
| 116 | Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: It has been shown that, in comparison to regularDNN training, training with stylized images reduces texture biases in imageclassification and improves robustness with respect to image corruptions. In aneffort to advance this line of research, we examine whether style transfer canlikewise deliver these two effects in semantic segmentation. |
Ben Hamscher; Edgar Heinert; Annika Mütze; Kira Maag; Matthias Rottmann; | arxiv-cs.CV | 2025-07-14 |
| 117 | Continuous‐Line Image Stylization Based on Hilbert Curve Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Horizontal and vertical lines hold significant aesthetic and psychological importance, providing a sense of order, stability, and security. This paper presents an image … |
Zhifang Tong; Bolei Zuov; Xiaoxia Yang; Shengjun Liu; Xinru Liu; | Computer Graphics Forum | 2025-07-01 |
| 118 | Surgical Neural Radiance Fields from One Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Methods: We leverage preoperative MRI data to define the set of cameraviewpoints and images needed for robust and unobstructed training.Intraoperatively, the appearance of the surgical image is transferred to thepre-constructed training set through neural style transfer, specificallycombining WTC2 and STROTSS to prevent over-stylization. |
Alberto Neri; Maximilan Fehrentz; Veronica Penza; Leonardo S. Mattos; Nazim Haouchine; | arxiv-cs.CV | 2025-07-01 |
| 119 | MSFD: Multiscale Feature Decomposition for Cross-Modality Visible-to-Infrared Drone Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the global landscape of the Internet of Things (IoT), drone IoT technology has gained widespread application. This technology can monitor and analyze land use and land cover … |
Xiaoning Chen; Zhiquan Liu; Zonghao Han; Mingyang Ma; Jian Zhao; | IEEE Internet of Things Journal | 2025-07-01 |
| 120 | LLMs Can See and Hear Without Any Training Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. |
Kumar Ashutosh; Yossi Gandelsman; Xinlei Chen; Ishan Misra; Rohit Girdhar; | icml | 2025-06-25 |
| 121 | Instability in Diffusion ODEs: An Explanation for Inaccurate Image Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we identify adeeper intrinsic property in the PF-ODE generation process, the instability,that can further amplify the reconstruction errors. |
HAN ZHANG et. al. | arxiv-cs.LG | 2025-06-23 |
| 122 | Break Stylistic Sophon: Are We Really Meant to Confine The Imagination in Style Transfer? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the framework for different tasks. |
GARY SONG YAN et. al. | arxiv-cs.CV | 2025-06-17 |
| 123 | Temporal Consistent Semantic Video Color Transfer from Multiple References Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Transferring the color from aesthetically high-quality reference color content to captured unpleasant color content is required for the media and entertainment industry. The … |
Aupendu Kar; Guan-Ming Su; | 2025 IEEE/CVF Conference on Computer Vision and Pattern … | 2025-06-11 |
| 124 | Synthetic Human Action Video Data Generation with Pose Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a method for generating synthetic human action video data using pose transfer (specifically, controllable 3D Gaussian avatar models). |
Vaclav Knapp; Matyas Bohacek; | arxiv-cs.CV | 2025-06-11 |
| 125 | Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SPARCL (Synthetic Perturbations for Advancing Robust Compositional Learning), which integrates image feature injection into a fast text-to-image generative model, followed by an image style transfer step, to meet the three challenges. |
Haoxin Li; Boyang Li; | cvpr | 2025-06-07 |
| 126 | Learning Flow Fields in Attention for Controllable Person Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Controllable person image generation aims to generate a person image conditioned on reference images, allowing precise control over the person’s appearance or pose.However, prior methods often distort fine-grained textural details from the reference image, despite achieving high overall image quality.We attribute these distortions to inadequate attention to corresponding regions in the reference image.To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training.Specifically, it is realized via a regularization loss on top of the attention map within a diffusion-based baseline.Our extensive experiments show that Leffa achieves state-of-the-art performance in controlling appearance (virtual try-on) and pose (pose transfer), significantly reducing fine-grained detail distortion while maintaining high image quality.Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models. |
ZIJIAN ZHOU et. al. | cvpr | 2025-06-07 |
| 127 | StyleMaster: Stylize Your Video with Artistic Generation and Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Style control has been popular in video generation models. Existing methods often generate videos far from the given style, cause content leakage, and struggle to transfer one … |
ZIXUAN YE et. al. | cvpr | 2025-06-07 |
| 128 | OmniStyle: Filtering High Quality Style Transfer Data at Scale Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce OmniStyle-1M, a large-scale paired style transfer dataset comprising over one million content-style-stylized image triplets across 1,000 diverse style categories, each enhanced with textual descriptions and instruction prompts. |
YE WANG et. al. | cvpr | 2025-06-07 |
| 129 | HistoFS: Non-IID Histopathologic Whole Slide Image Classification Via Federated Style Transfer with RoI-Preserving Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: (2) Performing style transfer may potentially shift the region of interests (RoIs) in the augmented WSIs. To address these challenges, we propose HistoFS, a federated learning framework for computational pathology on non-i.i.d. feature shifts in WSI classification. |
Farchan Hakim Raswa; Chun-Shien Lu; Jia-Ching Wang; | cvpr | 2025-06-07 |
| 130 | SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We argue that the root cause lies in their failure to consider the relationship between local regions and semantic regions. To address this issue, we propose a plug-and-play semantic continuous-sparse attention, dubbed SCSA, for arbitrary semantic style transfer—each query point considers certain key points in the corresponding semantic region. |
Chunnan Shang; Zhizhong Wang; Hongwei Wang; Xiangming Meng; | cvpr | 2025-06-07 |
| 131 | SGSST: Scaling Gaussian Splatting Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces SGSST: Scaling Gaussian Splatting Style Transfer, an optimization-based method to apply style transfer to pretrained 3DGS scenes. |
Bruno Galerne; Jianling Wang; Lara Raad; Jean-Michel Morel; | cvpr | 2025-06-07 |
| 132 | HSI: A Holistic Style Injector for Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Additionally, when processing large images, the quadratic complexity of the attention mechanism will bring high computational load. To alleviate above problems, we propose Holistic Style Injector (HSI), a novel attention-style transformation module to deliver artistic expression of target style. |
Shuhao Zhang; Hui Kang; Yang Liu; Fang Mei; Hongjuan Li; | cvpr | 2025-06-07 |
| 133 | StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through a series of experiments, we discovered that an effective startpoint in the sampling stage significantly enhances the style transfer process. Based on this discovery, we propose StyleSSP, which focuses on obtaining a better startpoint to address layout changes of original content and content leakage from style image. |
Ruojun Xu; Weijie Xi; XiaoDi Wang; Yongbo Mao; Zach Cheng; | cvpr | 2025-06-07 |
| 134 | V-Stylist: Video Stylization Via Collaboration and Reflection of MLLM Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the recent advancement in video stylization, most existing methods struggle to render any video with complex transitions,based on an open style description of user query.To fill this gap,we introduce a generic multi-agent system for video stylization, V-Stylist, by a novel collaboration and reflection paradigm of multi-modal large language models. |
Zhengrong Yue; Shaobin Zhuang; Kunchang Li; Yanbo Ding; Yali Wang; | cvpr | 2025-06-07 |
| 135 | StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Text-driven style transfer aims to merge the style of a reference image with content described by a text prompt. Recent advancements in text-to-image models have improved the nuance of style transformations, yet significant challenges remain, particularly with overfitting to reference styles, limiting stylistic control, and misaligning with textual content.In this paper, we propose three complementary strategies to address these issues. |
Mingkun Lei; Xue Song; Beier Zhu; Hao Wang; Chi Zhang; | cvpr | 2025-06-07 |
| 136 | LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present LineArt, a framework that transfers complex appearance onto detailed design drawings, facilitating design and artistic creation. |
XI WANG et. al. | cvpr | 2025-06-07 |
| 137 | Training-Free Identity Preservation in Stylized Image Generation Using Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This limitation is particularly acute for images where faces are small or exhibit significant camera-to-face distances, frequently leading to inadequate identity preservation. To address this, we introduce a novel, training-free framework for identity-preserved stylized image synthesis using diffusion models. |
Mohammad Ali Rezaei; Helia Hajikazem; Saeed Khanehgir; Mahdi Javanmardi; | arxiv-cs.CV | 2025-06-07 |
| 138 | Multi-StyleGS: Stylizing Gaussian Splatting with Multiple Styles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While 3D Gaussian Splatting(GS) has emerged as a promising and efficient method for realistic 3D scene modeling, there remains a challenge in adapting it to stylize 3D GS to match with multiple styles through automatic local style transfer or manual designation, while maintaining memory efficiency for stylization training. In this paper, we introduce a novel 3D GS stylization solution termed Multi-StyleGS to tackle these challenges. |
Yangkai Lin; Jiabao Lei; Kui jia; | arxiv-cs.CV | 2025-06-07 |
| 139 | PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Providing a dataset of 300k image-pairs and baseline evaluations for three different physical simulation tasks, we propose a benchmark to investigate the following research questions: i) are generative models able to learn complex physical relations from input-output image pairs? |
Martin Spitznagel; Jan Vaillant; Janis Keuper; | cvpr | 2025-06-07 |
| 140 | SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we develop a Mamba-based style transfer framework, termed SaMam. |
Hongda Liu; Longguang Wang; Ye Zhang; Ziru Yu; Yulan Guo; | cvpr | 2025-06-07 |
| 141 | DisenStyler: Text-driven Fast Image Stylization Using Content Disentanglement and Style Adaptive Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Huilin Liu; Qiong Fang; Caiping Xiang; Gaoming Yang; | Comput. Graph. | 2025-06-01 |
| 142 | Localized Adaptive Style Mixing for Feature Statistics Manipulation in Medical Image Translation with Limited Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Zhong Wang; Jiaxuan Jiang; Hao-Ran Wang; Ling Zhou; Yuee Li; | Expert Syst. Appl. | 2025-06-01 |
| 143 | Implicit Inversion Turns CLIP Into A Decoder Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we show that image synthesis is nevertheless possible using CLIP alone — without any decoder, training, or fine-tuning. |
ANTONIO D’ORAZIO et. al. | arxiv-cs.CV | 2025-05-29 |
| 144 | Training Free Stylized Abstraction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a training-free framework thatgenerates stylized abstractions from a single image using inference-timescaling in vision-language models (VLLMs) to extract identity-relevantfeatures, and a novel cross-domain rectified flow inversion strategy thatreconstructs structure based on style-dependent priors. |
Aimon Rahman; Kartik Narayan; Vishal M. Patel; | arxiv-cs.CV | 2025-05-28 |
| 145 | CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we introduce CLIPGaussians, the first unified style transfer framework that supports text- and image-guided stylization across multiple modalities: 2D images, videos, 3D objects, and 4D scenes. |
KORNEL HOWIL et. al. | arxiv-cs.CV | 2025-05-28 |
| 146 | StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, acquiring large volumes of such triplet data with specific styles is considerably more challenging than obtaining conventional text-to-image data used for training generative models. To address this issue, we propose StyleAR, an innovative approach that combines a specially designed data curation method with our proposed AR models to effectively utilize text-to-image binary data for style-aligned text-to-image generation. |
YI WU et. al. | arxiv-cs.CV | 2025-05-26 |
| 147 | Training-free Stylized Text-to-Image Generation with Fast Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although diffusion models exhibit impressive generative capabilities, existing methods for stylized image generation based on these models often require textual inversion or fine-tuning with style images, which is time-consuming and limits the practical applicability of large-scale diffusion models. To address these challenges, we propose a novel stylized image generation method leveraging a pre-trained large-scale diffusion model without requiring fine-tuning or any additional optimization, termed as OmniPainter. |
Xin Ma; Yaohui Wang; Xinyuan Chen; Tien-Tsin Wong; Cunjian Chen; | arxiv-cs.CV | 2025-05-25 |
| 148 | GT^2-GS: Geometry-aware Texture Transfer for Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present GT^2-GS, a geometry-aware texture transfer framework for gaussian splitting. |
Wenjie Liu; Zhongliang Liu; Junwei Shu; Changbo Wang; Yang Li; | arxiv-cs.CV | 2025-05-21 |
| 149 | Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we explore a diffusion-based framework for image-to-image translation by adapting Diffusion Transformers (DiT), which combine the denoising capabilities of diffusion models with the global modeling power of transformers. |
Qiang Zhu; Kuan Lu; Menghao Huo; Yuxiao Li; | arxiv-cs.CV | 2025-05-21 |
| 150 | 3D-Fixup: Advancing Photo Editing with 3D Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite significant advances in modeling image priors via diffusion models, 3D-aware image editing remains challenging, in part because the object is only specified via a single image. To tackle this challenge, we propose 3D-Fixup, a new framework for editing 2D images guided by learned 3D priors. |
YEN-CHI CHENG et. al. | arxiv-cs.CV | 2025-05-15 |
| 151 | ToonifyGB: StyleGAN-based Gaussian Blendshapes for 3D Stylized Head Avatars Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Toextend Toonify for synthesizing diverse stylized 3D head avatars using Gaussianblendshapes, we propose an efficient two-stage framework, ToonifyGB. |
Rui-Yang Ju; Sheng-Yen Huang; Yi-Ping Hung; | arxiv-cs.CV | 2025-05-15 |
| 152 | SPAST: Arbitrary Style Transfer with Style Priors Via Pre-trained Large-scale Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose a new framework, called SPAST, to generate high-quality stylized images with less inference time. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2025-05-13 |
| 153 | Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Vision-Language Model (VLM)-based augmentation techniques have been proven to be effective, but they require that the detector’s backbone has the same structure as the image encoder of VLM, limiting the detector framework selection. To address this problem, we propose Language-Driven Dual Style Mixing (LDDS) for single-domain generalization, which diversifies the source domain by fully utilizing the semantic information of the VLM. |
HONGDA QIN et. al. | arxiv-cs.CV | 2025-05-12 |
| 154 | Semantic Style Transfer for Enhancing Animal Facial Landmark Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study investigates the use of this technique for enhancing animal facial landmark detectors training. |
Anadil Hussein; Anna Zamansky; George Martvel; | arxiv-cs.CV | 2025-05-08 |
| 155 | RLMiniStyler: Light-weight RL Style Agent for Arbitrary Sequential Neural Style Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Still, existing deep learning-based methods often require significant computational costs to generate diverse stylized results. Motivated by this, we propose a novel reinforcement learning-based framework for arbitrary style transfer RLMiniStyler. |
JING HU et. al. | arxiv-cs.CV | 2025-05-07 |
| 156 | Deep Learning-based Style Transfer Research for Traditional Woodcut Paper Horse Art Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep learning (DL)-based style transfer techniques have been employed to modify traditional woodcut paper horse art images. This art form struggles to maintain its cultural … |
Qingfeng Shi; Jia Hou; | J. Comput. Methods Sci. Eng. | 2025-05-05 |
| 157 | Region-Aware Style Transfer Between Thangka Images Via Combined Segmentation and Adaptive Style Fusion Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Thangka is a unique intangible cultural heritage of the Tibet, with a long history and numerous schools, character-ized by distinctive techniques for depicting figures and … |
Yukai Xian; Te Shen; Yunjie Xiang; Pubu Danzeng; Yurui Lee; | 2025 28th International Conference on Computer Supported … | 2025-05-05 |
| 158 | Photoshop Batch Rendering Using Actions for Stylistic Video Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: My project looks at an efficient workflow for creative image/video editing using Adobe Photoshop Actions tool and Batch Processing System. This innovative approach to video editing through Photoshop creates a fundamental shift to creative workflow management through the integration of industry-leading image manipulation with video editing techniques. |
Tessa De La Fuente; | arxiv-cs.MM | 2025-05-02 |
| 159 | StyleMe3D: Stylization with Disentangled Priors By Multiple Encoders on 3D Gaussians Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose StyleMe3D, a holistic framework for 3D GS style transfer that integrates multi-modal style conditioning, multi-level semantic alignment, and perceptual quality enhancement. |
CAILIN ZHUANG et. al. | arxiv-cs.CV | 2025-04-21 |
| 160 | Can AI Recognize The Style of Art? Analyzing Aesthetics Through The Lens of Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we approach style transfer from an aesthetic perspective, thereby bridging AI techniques and aesthetics. |
Yunha Yeo; Daeho Um; | arxiv-cs.GR | 2025-04-19 |
| 161 | ICAS: IP Adapter and ControlNet-based Attention Structure for Multi-Subject Style Transfer Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, these methods often struggle with maintaining multi-subject semantic fidelity and are limited by high inference costs. To address these limitations, we propose ICAS (IP-Adapter and ControlNet-based Attention Structure), a novel framework for efficient and controllable multi-subject style transfer. |
Fuwei Liu; | arxiv-cs.CV | 2025-04-17 |
| 162 | Synchronized Multi‐Frame Diffusion for Temporally Consistent Video Stylization Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text‐guided video‐to‐video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text‐guided image diffusion … |
M. Xie; Hanyuan Liu; Chengze Li; Tien-Tsin Wong; | Computer Graphics Forum | 2025-04-16 |
| 163 | A High-Precision Character Cartoon Style Transfer Method Based on VToonify and Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods still have shortcomings in detail handling and character feature control. To address these issues, this paper proposes a high-precision character style transfer framework that combines the VToonify model with diffusion models. |
W. Wang; W. Wang; F. Bao; | icassp | 2025-04-15 |
| 164 | DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photorealistic images from source portraits in specific desired poses and appearances. |
E. Huang; Y. Zhang; F. Huang; G. Zhang; Y. Liu; | icassp | 2025-04-15 |
| 165 | One-Shot Learning for Pose-Guided Person Image Synthesis in The Wild Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, naively applying test-time tuning results in inconsistencies in facial identities and appearance attributes. To address this, we introduce a Visual Consistency Module (VCM), which enhances appearance consistency by combining the face, text, and image embedding. |
D. Fan; | icassp | 2025-04-15 |
| 166 | Simplified One-sided Image-to-Image Translation with Reconstruction-Constrained Generative Adversarial Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enhance both translational and reconstruction competencies, we propose using the discriminator’s encoding mechanism to retain the image’s attributes. |
S. Wang; Q. Wu; M. Ge; Y. Wang; | icassp | 2025-04-15 |
| 167 | DiffuseFIST: A Fast Image-guided Style Transfer Method for Adapting Large-scale Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they struggle to satisfy the user’s requirements due to (i) text’s inherent imprecision in expressing specific styles and (ii) generation is time-consuming due to many iterations in reverse process of diffusion models. To address these issues, we propose a fast style transfer method adopting pre-trained large-scale diffusion models, dubbed as DiffuseFIST, which adds T-small (300) noise to accelerate reverse process and solely requires real-world images and artistic images as input. |
M. Dai; Q. Zhou; R. Yi; L. Ma; | icassp | 2025-04-15 |
| 168 | Low-Rank Transformer Adaptation for Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although many methods have achieved remarkable results in style transfer, they typically rely on largescale datasets for training, which increases both the cost and complexity of data collection. To address this issue, we propose a Low-rank Transformer Adaptation method for style transfer which leverages the efficiency of low-rank adaptation to reduce the model’s complexity without compromising performance. |
W. Xu; M. Liu; B. Wen; | icassp | 2025-04-15 |
| 169 | Unsupervised Image-to-Image Style Transfer Via Dual-Condition Diffusion Models* Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Within the EDM framework, we have utilized cross-attention to design style and content embedding modules, overcoming instance alterations without the need for paired datasets and achieving high-resolution, high-fidelity results. |
A. Fan; J. Yang; W. Li; C. Zhang; | icassp | 2025-04-15 |
| 170 | Dual-Modality Guided Artistic Style Transfer with Pre-trained Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent approaches incorporating textual inversion offer more accurate style representations, but significant information loss occurs when transitioning between modalities. To address these issues, we propose Dual-Modality Guided Artistic Style Transfer (DMG), which makes full use of text and image information to enhance the visual effect and content consistency of stylized results. |
J. Liu; X. Xiong; J. Zhou; | icassp | 2025-04-15 |
| 171 | A Cost-effective Solution for Remote Sensing Image Segmentation Via Train/Test-Time Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: 2) Target-data Train-time Fine-tuning: We propose a joint positive and negative learning (JPNL) algorithm that adds both positive and negative samples to effectively learn domain-invariant knowledge from noisy pseudo-labeled target data. |
W. Chen; | icassp | 2025-04-15 |
| 172 | Data Augmentation Through Random Style Replacement IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. |
Qikai Yang; Cheng Ji; Huaiying Luo; Panfeng Li; Zhicheng Ding; | arxiv-cs.CV | 2025-04-14 |
| 173 | Trade-offs in Privacy-Preserving Eye Tracking Through Iris Obfuscation: A Benchmarking Study Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Considering all, in this paper, we benchmark blurring, noising, downsampling, rubber sheet model, and iris style transfer to obfuscate user identity, and compare their impact on image quality, privacy, utility, and risk of imposter attack on two datasets. |
Mengdi Wang; Efe Bozkir; Enkelejda Kasneci; | arxiv-cs.CV | 2025-04-14 |
| 174 | F-ViTA: Foundation Model Guided Visible to Thermal Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose F-ViTA, a novel approach that leverages the general world knowledge embedded in foundation models to guide the diffusion process for improved translation. |
Jay N. Paranjape; Celso de Melo; Vishal M. Patel; | arxiv-cs.CV | 2025-04-03 |
| 175 | Neural Style Transfer for Synthesising A Dataset of Ancient Egyptian Hieroglyphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a novel method for generating datasets of ancient Egyptian hieroglyphs by applying NST to a digital typeface. |
Lewis Matheson Creed; | arxiv-cs.LG | 2025-04-02 |
| 176 | SCFANet: Style Distribution Constraint Feature Alignment Network For Pathological Staining Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, the conversion from H&E to IHC images presents significant challenges, primarily due to alignment discrepancies between image pairs and the inherent diversity in IHC staining style patterns. To overcome these challenges, we propose the Style Distribution Constraint Feature Alignment Network (SCFANet), which incorporates two innovative modules: the Style Distribution Constrainer (SDC) and Feature Alignment Learning (FAL). |
Zetong Chen; Yuzhuo Chen; Hai Zhong; Xu Qiao; | arxiv-cs.CV | 2025-04-01 |
| 177 | Real Time Animator: High-Quality Cartoon Style Transfer in 6 Animation Styles on Images and Videos Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a comprehensive pipeline that integrates state-of-the-art techniques to achieve high-quality cartoon style transfer for educational images and videos. |
Liuxin Yang; Priyanka Ladha; | arxiv-cs.GR | 2025-04-01 |
| 178 | ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce ABC-GS, a novel framework based on 3D Gaussian Splatting to achieve high-quality 3D style transfer. |
Wenjie Liu; Zhongliang Liu; Xiaoyan Yang; Man Sha; Yang Li; | arxiv-cs.CV | 2025-03-28 |
| 179 | Semantix: An Energy Guided Sampler for Semantic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We subsequently propose a training-free method, Semantix an energy-guided sampler designed for Semantic Style Transfer that simultaneously guides both style and appearance transfer based on semantic understanding capacity of pre-trained diffusion models. |
Huiang He; Minghui Hu; Chuanxia Zheng; Chaoyue Wang; Tat-Jen Cham; | arxiv-cs.CV | 2025-03-28 |
| 180 | Tune It Up: Music Genre Transfer and Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this study, we adapt and improve CycleGAN model to perform music style transfer on Jazz and Classic genres. |
Fidan Samet; Oguz Bakir; Adnan Fidan; | arxiv-cs.SD | 2025-03-27 |
| 181 | Zero-Shot Visual Concept Blending Without Text Guidance Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a novel, zero-shot image generation technique called Visual Concept Blending that provides fine-grained control over which features from multiple reference images are transferred to a source image. |
Hiroya Makino; Takahiro Yamaguchi; Hiroyuki Sakai; | arxiv-cs.CV | 2025-03-27 |
| 182 | Pluggable Style Representation Learning for Multi-Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, the additional computational cost introduced by more model parameters hinders these methods to be deployed on resource-limited devices. To address this challenge, in this paper, we develop a style transfer framework by decoupling the style modeling and transferring. |
Hongda Liu; Longguang Wang; Weijun Guan; Ye Zhang; Yulan Guo; | arxiv-cs.CV | 2025-03-26 |
| 183 | ReverBERT: A State Space Model for Efficient Text-Driven Speech Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, wepresent \emph{ReverBERT}, an efficient framework for text-driven speech styletransfer that draws inspiration from a state space model (SSM) paradigm,loosely motivated by the image-based method of Wang andLiu~\cite{wang2024stylemamba}. |
Michael Brown; Sofia Martinez; Priya Singh; | arxiv-cs.GR | 2025-03-26 |
| 184 | SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, these methods face challenges such as poor transferability, high computational costs, and the introduction of noticeable noise, which compromises the aesthetic quality of the original artwork. To address these limitations, we propose a Structurally Imperceptible and Transferable Adversarial (SITA) attacks. |
JINGDAN KANG et. al. | arxiv-cs.CV | 2025-03-25 |
| 185 | Multi-Prompt Style Interpolation for Fine-Grained Artistic Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose anovel \emph{multi-prompt style interpolation} framework that extends therecently introduced \textbf{StyleMamba} approach. |
Lei Chen; Hao Li; Yuxin Zhang; Chao Li; Kai Wen; | arxiv-cs.GR | 2025-03-20 |
| 186 | Free-Lunch Color-Texture Disentanglement for Stylized Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces thefirst tuning-free approach to achieve free-lunch color-texture disentanglementin stylized T2I generation, addressing the need for independently controlledstyle elements for the Disentangled Stylized Image Generation (DisIG) problem.Our approach leverages the Image-Prompt Additivity property in the CLIP imageembedding space to develop techniques for separating and extractingColor-Texture Embeddings (CTE) from individual color and texture referenceimages. |
JIANG QIN et. al. | arxiv-cs.CV | 2025-03-18 |
| 187 | Less Is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, current state-of-the-art methods often struggle to disentangle content and style from style-reference images, leading to issues such as content leakages. To address this issue, we propose a masking-based method that efficiently decouples content from style without the need of tuning any model parameters. |
Lin Zhu; Xinbing Wang; Chenghu Zhou; Qinying Gu; Nanyang Ye; | iclr | 2025-03-17 |
| 188 | Semantix: An Energy-guided Sampler for Semantic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We subsequently propose a training-free method, *Semantix*, an energy-guided sampler designed for Semantic Style Transfer that simultaneously guides both style and appearance transfer based on semantic understanding capacity of pre-trained diffusion models. |
Huiang He; Minghui Hu; Chuanxia Zheng; Chaoyue Wang; Tat-Jen Cham; | iclr | 2025-03-17 |
| 189 | Generalized Consistency Trajectory Models for Image Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Thus, this work aims to unlock the full potential of CTMs by proposing generalized CTMs (GCTMs), which translate between arbitrary distributions via ODEs. |
Beomsu Kim; Jaemin Kim; Jeongsol Kim; Jong Chul Ye; | iclr | 2025-03-17 |
| 190 | Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, applying ControlNets independently to different frames can not effectively maintain object temporal consistency. To address these challenges, we introduce Ctrl-Adapter, an efficient and versatile framework that adds diverse controls to any image/video diffusion models through the adaptation of pretrained ControlNets. |
Han Lin; Jaemin Cho; Abhay Zala; Mohit Bansal; | iclr | 2025-03-17 |
| 191 | Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present an algorithm named pairwise sample optimization (PSO), which enables the direct fine-tuning of an arbitrary timestep-distilled diffusion model. |
ZICHEN MIAO et. al. | iclr | 2025-03-17 |
| 192 | Shape Bias and Robustness Evaluation Via Cue Decomposition for Image Classification and Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we provide a new evaluation procedure consisting of 1) a cue-decomposition method that comprises two AI-free data pre-processing methods extracting shape and texture cues, respectively, and 2) a novel cue-decomposition shape bias evaluation metric that leverages the cue-decomposition data. |
Edgar Heinert; Thomas Gottwald; Annika Mütze; Matthias Rottmann; | arxiv-cs.CV | 2025-03-16 |
| 193 | Text-Driven Video Style Transfer with State-Space Models: Extending StyleMamba for Temporal Coherence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: StyleMamba has recently demonstrated efficient text-driven image styletransfer by leveraging state-space models (SSMs) and masked directional losses.In this paper, we extend the StyleMamba framework to handle video sequences. |
Chao Li; Minsu Park; Cristina Rossi; Zhuang Li; | arxiv-cs.GR | 2025-03-15 |
| 194 | UStyle: Waterbody Style Transfer of Underwater Scenes By Depth-Guided Feature Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper introduces UStyle, the first data-driven learning framework for transferring waterbody styles across underwater images without requiring prior reference images or scene information. |
Md Abu Bakr Siddique; Vaishnav Ramesh; Junliang Liu; Piyush Singh; Md Jahidul Islam; | arxiv-cs.CV | 2025-03-14 |
| 195 | Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite their widespread use, existing avatar platforms face significant limitations, including restricted expressivity due to predefined assets, tedious customization processes, or inefficient rendering requirements. Addressing these shortcomings, we introduce Snapmoji, an avatar generation system that instantly creates animatable, dual-stylized avatars from a selfie. |
ERIC M. CHEN et. al. | arxiv-cs.GR | 2025-03-14 |
| 196 | Deepfake Detection of Face Images Based on A Convolutional Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We want to address this conflict by building a model based on a Convolutions Neural Network in order to detect such generated and fake images showing human portraits. As a basis, we use a pre-trained ResNet-50 model due to its effectiveness in terms of classifying images. |
Lukas Kroiß; Johannes Reschke; | arxiv-cs.CV | 2025-03-14 |
| 197 | ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we comprehensively analyze the limitations of the standard diffusion parameterization, which learns to predict noise, in the context of style transfer. |
BOLIN CHEN et. al. | arxiv-cs.CV | 2025-03-13 |
| 198 | MoEdit: On Learning Quantity Perception for Multi-object Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, existing methods often struggle to consider each object both individually and part of the whole image editing, both of which are crucial for ensuring consistent quantity perception, resulting in suboptimal perceptual performance. To address these challenges, we propose MoEdit, an auxiliary-free multi-object image editing framework. |
YANFENG LI et. al. | arxiv-cs.CV | 2025-03-13 |
| 199 | InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents InteractEdit, a novel framework for zero-shot Human-Object Interaction (HOI) editing, addressing the challenging task of transforming an existing interaction in an image into a new, desired interaction while preserving the identities of the subject and object. |
JIUN TIAN HOE et. al. | arxiv-cs.GR | 2025-03-12 |
| 200 | DyArtbank: Diverse Artistic Style Transfer Via Pre-trained Stable Diffusion and Dynamic Style Prompt Artbank IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing style transfer methods can only render consistent artistic stylized images, making it difficult for users to get enough stylized images to enjoy. To solve this issue, we propose a novel artistic style transfer framework called DyArtbank, which can generate diverse and highly realistic artistic stylized images. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2025-03-11 |
| 201 | FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present FPGS, a feed-forward photorealistic style transfer method of large-scale radiance fields represented by Gaussian Splatting. |
GeonU Kim; Kim Youwang; Lee Hyoseok; Tae-Hyun Oh; | arxiv-cs.GR | 2025-03-11 |
| 202 | U-StyDiT: Ultra-high Quality Artistic Style Transfer Using Diffusion Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although these methods can generate some artistic stylized images, they still exhibit obvious artifacts and disharmonious patterns, which hinder their ability to produce ultra-high quality artistic stylized images. To address these issues, we propose a novel artistic image style transfer method, U-StyDiT, which is built on transformer-based diffusion (DiT) and learns content-style disentanglement, generating ultra-high quality artistic stylized images. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2025-03-11 |
| 203 | GAS-NeRF: Geometry-Aware Stylization of Dynamic Radiance Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing style transfer methods primarily target appearance — such as color and texture transformation — but often neglect the geometric characteristics of the style image, which are crucial for achieving a complete and coherent stylization effect. To overcome these shortcomings, we propose GAS-NeRF, a novel approach for joint appearance and geometry stylization in dynamic Radiance Fields. |
Nhat Phuong Anh Vu; Abhishek Saroha; Or Litany; Daniel Cremers; | arxiv-cs.CV | 2025-03-11 |
| 204 | LBM: Latent Bridge Matching for Fast Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce Latent Bridge Matching (LBM), a new, versatileand scalable method that relies on Bridge Matching in a latent space to achievefast image-to-image translation. |
Clément Chadebec; Onur Tasar; Sanjeev Sreetharan; Benjamin Aubin; | arxiv-cs.CV | 2025-03-10 |
| 205 | SOYO: A Tuning-Free Approach for Video Style Morphing Via Style-Adaptive Interpolation in Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current approaches often generate stylized video frames with discontinuous structures and abrupt style changes when handling such transitions. To address these limitations, we introduce SOYO, a novel diffusion-based framework for video style morphing. |
HAOYU ZHENG et. al. | arxiv-cs.CV | 2025-03-10 |
| 206 | Balanced Image Stylization with Style Matching Score Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Style Matching Score (SMS), a novel optimization method for imagestylization with diffusion models. |
YUXIN JIANG et. al. | arxiv-cs.CV | 2025-03-10 |
| 207 | Inversion-Free Video Style Transfer with Trajectory Reset Attention Control and Content-Style Bridging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Trajectory Reset Attention Control (TRAC), a novel method that allows for high-quality style transfer while preserving content integrity. |
Jiang Lin; Zili Yi; | arxiv-cs.CV | 2025-03-10 |
| 208 | AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: While diffusion models have achieved remarkable progress in style transfer tasks, existing methods typically rely on fine-tuning or optimizing pre-trained models during inference, leading to high computational costs and challenges in balancing content preservation with style integration. To address these limitations, we introduce AttenST, a training-free attention-driven style transfer framework. |
Bo Huang; Wenlun Xu; Qizhuo Han; Haodong Jing; Ying Li; | arxiv-cs.CV | 2025-03-10 |
| 209 | TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Diffusion Transformers (DiTs) are a powerful yet underexplored class ofgenerative models compared to U-Net-based diffusion architectures. We proposeTIDE-Temporal-aware sparse … |
VICTOR SHEA-JAY HUANG et. al. | arxiv-cs.CV | 2025-03-10 |
| 210 | ObjMST: An Object-Focused Multimodal Style Transfer Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose ObjMST, an object-focused multimodal style transfer framework that provides separate style supervision for salient objects and surrounding elements while addressing alignment issues in multimodal representation learning. |
Chanda Grover Kamra; Indra Deep Mastan; Debayan Gupta; | arxiv-cs.CV | 2025-03-06 |
| 211 | Seeing Eye to AI? Applying Deep-Feature-Based Similarity Metrics to Information Visualization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent studies show deep-feature-based similarity metrics correlate well with perceptual judgments of image similarity and serve as effective loss functions for tasks like image super-resolution and style transfer. We explore the application of such metrics to judgments of visualization similarity. |
Sheng Long; Angelos Chatzimparmpas; Emma Alexander; Matthew Kay; Jessica Hullman; | arxiv-cs.HC | 2025-02-28 |
| 212 | D-LUT: Photorealistic Style Transfer Via Diffusion Process Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Post-editing color in photographs is a crucial process for enhancing a photograph’s aesthetic value. Traditionally, this process has required a significant investment of time and … |
Mujing Li; Guanjie Wang; Xingguang Zhang; Qifeng Liao; Chenxi Xiao; | 2025 IEEE/CVF Winter Conference on Applications of Computer … | 2025-02-26 |
| 213 | VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a novel fine-grained pixel-level image editing method based on pre-trained diffusion models. |
HAOCUN YE et. al. | aaai | 2025-02-25 |
| 214 | Multi-StyleGS: Stylized Gaussian Splatting with Multiple Styles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While 3D Gaussian Splatting (GS) has emerged as a promising and efficient method for realistic 3D scene modeling, there remains a challenge in adapting it to stylize 3D GS to match with multiple styles through automatic local style transfer or manual designation, while maintaining memory efficiency for stylization training. In this paper, we introduce a novel 3D GS stylization solution termed Multi-StyleGS to tackle these challenges. |
Yangkai Lin; Jiabao Lei; Kui Jia; | aaai | 2025-02-25 |
| 215 | Style Nursing with Spatial and Semantic Guidance for Zero-Shot Traffic Scene Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Especially when applied to complex traffic scenes with diverse objects, layouts, and stylistic variations, current diffusion models tend to exhibit Style Neglection, i.e., failing to generate the required style in the prompt. To address this issue, we propose Style Nursing, which directs the model to focus on style subject tokens in the text prompt and excites their corresponding visual activations. |
Zhen Wang; Zihang Lin; Meng Yuan; Yuehu Liu; Chi Zhang; | aaai | 2025-02-25 |
| 216 | Unpaired Multi-Domain Histopathology Virtual Staining Using Dual Path Prompted Inversion Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Furthermore, the unpaired characteristic of virtual staining data may compromise the preservation of pathological diagnostic content. To address these challenges, we propose a dual-path inversion virtual staining method using prompt learning, which optimizes visual prompts to control content and style, while preserving complete pathological diagnostic content. |
BING XIONG et. al. | aaai | 2025-02-25 |
| 217 | SigStyle: Signature Style Transfer Via Personalized Text-to-Image Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce SigStyle, a framework that leverages the semantic priors that embedded in a personalized text-to-image diffusion model to capture the signature style representation. |
YE WANG et. al. | aaai | 2025-02-25 |
| 218 | IDseq: Decoupled and Sequentially Detecting and Grounding Multi-Modal Media Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods have not sufficiently explored the intrinsic properties of the manipulated images, which contain both forgery and content features, leading to inefficient utilization. To address this problem, we propose an Image-Driven Decoupled Sequential Framework (IDseq), designed to decouple image features and rationally integrate them to accomplish different sub-tasks effectively. |
Runxin Liu; Tian Xie; Jiaming Li; Lingyun Yu; Hongtao Xie; | aaai | 2025-02-25 |
| 219 | PQDAST: Depth-Aware Arbitrary Style Transfer for Games Via Perceptual Quality-Guided Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present PQDAST, the first solution to address this. |
Eleftherios Ioannou; Steve Maddock; | arxiv-cs.CV | 2025-02-24 |
| 220 | IBURD: Image Blending for Underwater Robotic Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an image blending pipeline, \textit{IBURD}, that creates realistic synthetic images to assist in the training of deep detectors for use on underwater autonomous vehicles (AUVs) for marine debris detection tasks. |
Jungseok Hong; Sakshi Singh; Junaed Sattar; | arxiv-cs.CV | 2025-02-24 |
| 221 | PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce PhotoDoodle, a novel image editing framework designed to facilitate photo doodling by enabling artists to overlay decorative elements onto photographs. |
SHIJIE HUANG et. al. | arxiv-cs.CV | 2025-02-20 |
| 222 | Image Inversion: A Survey from GANs to Diffusion and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: By synthesizing the latest developments, this paper aims to provide researchers and practitioners with a valuable reference resource, promoting further advancements in the field of image inversion. |
YINAN CHEN et. al. | arxiv-cs.CV | 2025-02-17 |
| 223 | Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We demonstrate that discriminative models inherently contain powerful generative capabilities, challenging the fundamental distinction between discriminative and generative architectures. |
Stanislav Fort; Jonathan Whitaker; | arxiv-cs.CV | 2025-02-11 |
| 224 | Application of CycleGAN-based Image Style Transfer Algorithm in Visual Communication Design Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This paper addresses the challenges in traditional image style transfer research, including high design costs, reliance on paired data, limited transfer effects, and a lack of … |
Ying Zhao; | Journal of Computational Methods in Sciences and Engineering | 2025-02-10 |
| 225 | Coarse-to-Fine Structure-Aware Artistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present an effective method that can be used to transfer style patterns while fusing the local style structure into the local content structure. |
Kunxiao Liu; Guowu Yuan; Hao Wu; Wenhua Qian; | arxiv-cs.CV | 2025-02-07 |
| 226 | ImprovNet — Generating Controllable Musical Improvisations with Iterative Corruption Refinement Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper presents ImprovNet, a transformer-based architecture that generates expressive and controllable musical improvisations through a self-supervised corruption-refinement training strategy. |
KESHAV BHANDARI et. al. | arxiv-cs.SD | 2025-02-06 |
| 227 | Multiscale Style Transfer Based on A Laplacian Pyramid for Traditional Chinese Painting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present a novel effective multiscale style transfer method based on Laplacian pyramid decomposition and reconstruction, which can transfer unique patterns of Chinese paintings by learning different image features at different scales. |
Kunxiao Liu; Guowu Yuan; Hongyu Liu; Hao Wu; | arxiv-cs.CV | 2025-02-06 |
| 228 | Generative Adversarial Networks Bridging Art and Machine Intelligence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The text systematically addresses the mathematical and theoretical underpinnings including probability theory, statistics, and game theory providing a solid framework for understanding the objectives, loss functions, and optimisation challenges inherent to GAN training. |
JUNHAO SONG et. al. | arxiv-cs.LG | 2025-02-06 |
| 229 | ImprovNet – Generating Controllable Musical Improvisations with Iterative Corruption Refinement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Despite deep learning’s remarkable advances in style transfer across various domains, generating controllable performance-level musical style transfer for complete symbolically … |
KESHAV BHANDARI et. al. | 2025 International Joint Conference on Neural Networks … | 2025-02-06 |
| 230 | Volumetric Temporal Texture Synthesis for Smoke Stylization Using Neural Cellular Automata Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Artistic stylization of 3D volumetric smoke data is still a challenge in computer graphics due to the difficulty of ensuring spatiotemporal consistency given a reference style … |
Dongqing Wang; Ehsan Pajouheshgar; Yitao Xu; Tong Zhang; Sabine Süsstrunk; | ArXiv | 2025-02-05 |
| 231 | TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis reveals that this limitation primarily stems from the conditional diffusion model’s attention modules failing to adequately capture and preserve clothing patterns. To address this limitation, we propose human-parsing-guided attention diffusion, a novel approach that effectively preserves both facial and clothing appearance while generating high-quality results. |
Zhihong Xu; Dongxia Wang; Peng Du; Yang Cao; Qing Guo; | arxiv-cs.CV | 2025-02-05 |
| 232 | Estimating Forest Carbon Stocks from High-resolution Remote Sensing Imagery By Reducing Domain Shift with Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Using the style transfer method, we introduced Swin Transformer to extract global features through attention mechanisms, converting the carbon stock estimation into an image translation. |
Zhenyu Yu; Jinnian Wang; | arxiv-cs.CV | 2025-02-02 |
| 233 | A Diffusion Model Translator for Efficient Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an efficient method that equips a diffusion model with a lightweight translator, dubbed a Diffusion Model Translator (DMT), to accomplish I2I. |
Mengfei Xia; Yu Zhou; Ran Yi; Yong-Jin Liu; Wenping Wang; | arxiv-cs.CV | 2025-01-31 |
| 234 | Generative AI for Vision: A Comprehensive Study of Frameworks and Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work presents a structured classification of image generation techniques based on the nature of the input, organizing methods by input modalities like noisy vectors, latent representations, and conditional inputs. |
Fouad Bousetouane; | arxiv-cs.CV | 2025-01-29 |
| 235 | Can Pose Transfer Models Generate Realistic Human Motion? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In a controlled environment of 20 distinct human actions, we find that participants, presented with the pose-transferred videos, correctly identify the desired action only 42.92% of the time. |
Vaclav Knapp; Matyas Bohacek; | arxiv-cs.CV | 2025-01-26 |
| 236 | Training-Free Style and Content Transfer By Leveraging U-Net Skip Connections in Stable Diffusion 2 IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent advances in diffusion models for image generation have led to detailed examinations of several components within the U-Net architecture for image editing. While previous … |
Ludovica Schaerf; Andrea Alfarano; Fabrizio Silvestri; L. Impett; | ArXiv | 2025-01-24 |
| 237 | Training-Free Style and Content Transfer By Leveraging U-Net Skip Connections in Stable Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We conduct thorough analyses on the role of the skip connections and find that the residual connections passed by the third encoder block carry most of the spatial information of the reconstructed image, splitting the content from the style, passed by the remaining stream in the opposed decoding layer. |
Ludovica Schaerf; Andrea Alfarano; Fabrizio Silvestri; Leonardo Impett; | arxiv-cs.CV | 2025-01-24 |
| 238 | Dynamic Neural Style Transfer for Artistic Image Generation Using VGG19 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Nevertheless, a number of current techniques continue to encounter obstacles, including lengthy processing times, restricted choices of style images, and the inability to modify the weight ratio of styles. We proposed a neural style transfer system that can add various artistic styles to a desired image to address these constraints allowing flexible adjustments to style weight ratios and reducing processing time. |
Kapil Kashyap; Mehak Garg; Sean Fargose; Sindhu Nair; | arxiv-cs.CV | 2025-01-16 |
| 239 | CaVIT: An Integrated Method for Image Style Transfer Using Parallel CNN and Vision Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Zaifang Zhang; Shunlu Lu; Qing Guo; Nan Gao; YuXiao Yang; | Appl. Intell. | 2025-01-13 |
| 240 | Improving Image Captioning By Mimicking Human Reformulation Feedback at Inference-time Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a novel type of feedback — caption reformulations — and train models to mimic reformulation feedback based on human annotations. |
Uri Berger; Omri Abend; Lea Frermann; Gabriel Stanovsky; | arxiv-cs.CV | 2025-01-08 |
| 241 | ZDySS – Zero-Shot Dynamic Scene Stylization Using Gaussian Splatting Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Stylizing a dynamic scene based on an exemplar image is critical for various real-world applications, including gaming, filmmaking, and augmented and virtual reality. However, … |
ABHISHEK SAROHA et. al. | ArXiv | 2025-01-07 |
| 242 | ZDySS — Zero-Shot Dynamic Scene Stylization Using Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ZDySS, a zero-shot stylization framework for dynamic scenes, allowing our model to generalize to previously unseen style images at inference. |
ABHISHEK SAROHA et. al. | arxiv-cs.CV | 2025-01-07 |
| 243 | Aesthetic Matters in Music Perception for Image Stylization: A Emotion-driven Music-to-Visual Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Similarly, music research largely focuses on theoretical aspects, with limited exploration of its emotional dimensions and their integration with visual arts. To address these gaps, we introduce EmoMV, an emotion-driven music-to-visual manipulation method that manipulates images based on musical emotions. |
JUNJIE XU et. al. | arxiv-cs.CV | 2025-01-03 |
| 244 | ArtCrafter: Text-Image Aligning Style Transfer Via Embedding Reframing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, despite their capabilities, direct conditional guidance approaches often face challenges in balancing the expressiveness of textual semantics with the diversity of output results while capturing stylistic features. To address these challenges, we introduce ArtCrafter, a novel framework for text-to-image style transfer. |
NISHA HUANG et. al. | arxiv-cs.CV | 2025-01-03 |
| 245 | Haar Wavelet-Based Representation Learning for Unpaired Image-to-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In recent years, there have been numerous attempts to achieve unpaired image-to-image translation. Many algorithms have especially incorporated the contrastive learning framework … |
Soobin Park; Seohyeon Yoo; Nabin Jeong; Eunju Cha; | IEEE Access | 2025-01-01 |
| 246 | Shade Artifact Reduction in CBCT-to-MDCT: Fine-Tuning Based on Style Transfer and Human Feedback Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Cone beam computed tomography (CBCT) is widely used in dental treatment due to its low radiation dose and cost. However, it has lower image quality compared to Multi Detector … |
Hyun-Cheol Park; Kiwan Jeon; Hyoung Suk Park; Sung Ho Kang; | IEEE Access | 2025-01-01 |
| 247 | AplusN: Progressively Integrating Attention and Normalization in Wavelet Domain for Pose Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Pose-guided person image generation aims to synthesize images of human in various poses, often encountering issues such as occlusions and texture transfers. Previous methods have … |
Wei Yu; Rui Wang; Weizhi Yang; Wenjian Hu; Wei Xiang; | IEEE Transactions on Multimedia | 2025-01-01 |
| 248 | Exploration and Validation of Specialized Loss Functions for Generative Visual-Thermal Image Domain Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: : This paper presents an enhanced approach to visual-to-thermal image translation using an improved InfraGAN model, incorporating additional loss functions to increase realism and … |
Simon Fischer; B. Kottler; Eva Strauss; Dimitri Bulatov; | VISIGRAPP : VISAPP | 2025-01-01 |
| 249 | Color Consistency Anime Style Transfer Based on Hybrid Structural Decomposition Network Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the anime industry, character design frequently encounters challenges such as oversimplification and homogenization, which severely restrict the diversity and creativity of … |
Jun Zhang; Yunhua Zhang; | IEEE Access | 2025-01-01 |
| 250 | Bridging The Metrics Gap in Image Style Transfer: A Comprehensive Survey of Models and Criteria Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Xiaotong Zhou; Yuhui Zheng; Junming Yang; | Neurocomputing | 2025-01-01 |
| 251 | Zero-Shot Text-Driven Dynamic Neural Radiance Fields Stylization Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text-driven style transfer for Neural Radiance Fields (NeRFs) is an emerging research topic that leverages text descriptions instead of reference style images to apply style … |
Wanlin Liang; Hongbin Xu; Wanshui Gan; Wenxiong Kang; | IEEE Transactions on Multimedia | 2025-01-01 |
| 252 | MCAFNet: Multiscale Channel Attention Fusion Network for Arbitrary Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, attention-based arbitrary style transfer (AST) techniques have been widely applied in image generation and video processing. However, the scale bias of the attention … |
Zhongyu Bai; Hongli Xu; Qichuan Ding; Xiangyue Zhang; | IEEE Transactions on Instrumentation and Measurement | 2025-01-01 |
| 253 | QRS-Trs: Style Transfer-Based Image-to-Image Translation for Carbon Stock Estimation in Quantitative Remote Sensing IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Forests serve as vital carbon reservoirs, reducing atmospheric CO2 and mitigating climate change. Monitoring carbon stocks typically combines ground-based data with satellite … |
Zhenyu Yu; Jinnian Wang; Hanqing Chen; Mohd Yamani Idna Idris; | IEEE Access | 2025-01-01 |
| 254 | Image Style Transfer-Based Data Augmentation for Sanitary Ceramic Defect Detection Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the task of surface defect detection on sanitary ceramics, the production environment poses limitations. There are obvious differences between the image data we collected and … |
Jingfan Hang; Xianqiang Yang; Chao Ye; | IEEE Transactions on Instrumentation and Measurement | 2025-01-01 |
| 255 | GFTT: Geographical Feature Tokenization Transformer for SAR-to-Optical Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Synthetic aperture radar (SAR) image to optical image translation not only assists information interpretability, but also fills the gaps in optical applications due to weather and … |
Hongbo Liang; Xuezhi Yang; Xiangyu Yang; Jinjin Luo; Jiajia Zhu; | IEEE Journal of Selected Topics in Applied Earth … | 2025-01-01 |
| 256 | StyleRWKV: High-Quality and High-Efficiency Style Transfer with RWKV-like Architecture Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a novel framework StyleRWKV, to achieve high-quality style transfer with limited memory usage and linear time complexity. |
Miaomiao Dai; Qianyu Zhou; Lizhuang Ma; | arxiv-cs.CV | 2024-12-27 |
| 257 | DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. |
Enbo Huang; Yuan Zhang; Faliang Huang; Guangyu Zhang; Yang Liu; | arxiv-cs.CV | 2024-12-25 |
| 258 | Single Trajectory Distillation for Accelerating Image and Video Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This training strategy can not ensure the consistency of whole trajectories. To address this issue, we propose single trajectory distillation (STD) starting from a specific partial noise state. |
SIJIE XU et. al. | arxiv-cs.CV | 2024-12-25 |
| 259 | Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a novel method to identifysensitivities within the DDPM attention layers, identifying specific layersthat correspond to different stylistic aspects. |
Nadav Z. Cohen; Oron Nir; Ariel Shamir; | arxiv-cs.CV | 2024-12-25 |
| 260 | Ensuring Consistency for In-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The former entails incorporating image information during translation, while the latter involves maintaining consistency between the style of the text-image and the original image, ensuring background integrity. To address these consistency requirements, we introduce a novel two-stage framework named HCIIT (High-Consistency In-Image Translation) which involves text-image translation using a multimodal multilingual large language model in the first stage and image backfilling with a diffusion model in the second stage. |
CHENGPENG FU et. al. | arxiv-cs.CL | 2024-12-23 |
| 261 | Style Transfer Dataset: What Makes A Good Stylization? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a new dataset with the goal of advancing image style transfer – the task of rendering one image in the style of another image. |
Victor Kitov; Valentin Abramov; Mikhail Akhtyrchenko; | arxiv-cs.CV | 2024-12-22 |
| 262 | Diffusion-Based Conditional Image Editing Through Optimized Inference with Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. |
Hyunsoo Lee; Minsoo Kang; Bohyung Han; | arxiv-cs.CV | 2024-12-20 |
| 263 | Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This issue is particularly pronounced in transportation applications, such as detecting vehicles and other objects of interest on rural roads at night, where street lighting is often absent, and headlights may introduce undesirable glare. This study addresses these challenges by introducing a novel framework for labeling-free data augmentation, leveraging CARLA-generated synthetic data for day-to-night image style transfer. |
Yunxiang Yang; Hao Zhen; Yongcan Huang; Jidong J. Yang; | arxiv-cs.CV | 2024-12-20 |
| 264 | WikiStyle+: A Multimodal Approach to Content-Style Representation Disentanglement for Artistic Image Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current methods for content and style disentanglement primarily rely on image supervision, which leads to two problems: 1) models can only support one modality for style or content input;2) incomplete disentanglement resulting in content leakage from the reference image. To address the above issues, this paper proposes a multimodal approach to content-style disentanglement for artistic image stylization. |
Ma Zhuoqi; Zhang Yixuan; You Zejun; Tian Long; Liu Xiyang; | arxiv-cs.CV | 2024-12-18 |
| 265 | Prompt Augmentation for Self-supervised Text-guided Image Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In response, our work introduces prompt augmentation, a method amplifying a single input prompt into several target prompts, strengthening textual context and enabling localised image editing. |
Rumeysa Bodur; Binod Bhattarai; Tae-Kyun Kim; | arxiv-cs.CV | 2024-12-17 |
| 266 | UnMA-CapSumT: Unified and Multi-Head Attention-driven Caption Summarization Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To the best of our knowledge, no such work exists that provided a description that integrates different captioning methods to describe the contents of an image with factual and stylized (romantic and humorous) elements. To overcome these limitations, this paper presents a novel Unified Attention and Multi-Head Attention-driven Caption Summarization Transformer (UnMA-CapSumT) based Captioning Framework. |
Dhruv Sharma; Chhavi Dhiman; Dinesh Kumar; | arxiv-cs.CV | 2024-12-16 |
| 267 | Learning Flow Fields in Attention for Controllable Person Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We attribute these distortions to inadequate attention to corresponding regions in the reference image. To address this, we thereby propose learning flow fields in attention (Leffa), which explicitly guides the target query to attend to the correct reference key in the attention layer during training. |
ZIJIAN ZHOU et. al. | arxiv-cs.CV | 2024-12-11 |
| 268 | Using Pix2Pix Conditional Generative Adversarial Networks to Generate Personalized Poster Content: Style Transfer and Detail Enhancement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the process of generating personalized poster content, there are often problems such as inconsistency, blurring, and distortion between the generated image and the original … |
RUI TIAN et. al. | Journal of Computational Methods in Sciences and Engineering | 2024-12-10 |
| 269 | StyleMark: A Robust Watermarking Method for Art Style Images Against Black-Box Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unfortunately, AST-generated images lose the structural and semantic information of the original style image, hindering end-to-end robust tracking by watermarks. To fill this gap, we propose StyleMark, the first robust watermarking method for black-box AST, which can be seamlessly applied to art style images achieving precise attribution of artistic styles after AST. |
Yunming Zhang; Dengpan Ye; Sipeng Shen; Jun Wang; | arxiv-cs.CV | 2024-12-09 |
| 270 | Image Style Transfer with Saliency Constrained and SIFT Feature Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Yaqi Sun; Xiaolan Xie; Zhi Li; Huihuang Zhao; | Vis. Comput. | 2024-12-07 |
| 271 | Continuous Video Process: Modeling Videos As Continuous Multi-Dimensional Processes for Video Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our paper, we introduce a novel model class, that treats video as a continuous multi-dimensional process rather than a series of discrete frames. |
Gaurav Shrivastava; Abhinav Shrivastava; | arxiv-cs.CV | 2024-12-06 |
| 272 | D-LORD for Motion Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces a novel framework named D-LORD (Double Latent Optimization for Representation Disentanglement), which is designed for motion stylization (motion style transfer and motion retargeting). |
Meenakshi Gupta; Mingyuan Lei; Tat-Jen Cham; Hwee Kuan Lee; | arxiv-cs.CV | 2024-12-05 |
| 273 | Learning Artistic Signatures: Symmetry Discovery and Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Conversely, more recent work with diffusion models offers compelling empirical results but provides little theoretical grounding. To address these issues, we propose an alternative definition of artistic style. |
Emma Finn; T. Anderson Keller; Emmanouil Theodosis; Demba E. Ba; | arxiv-cs.CV | 2024-12-05 |
| 274 | SGSST: Scaling Gaussian Splatting StyleTransfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This work introduces SGSST: Scaling Gaussian Splatting Style Transfer, an optimization-based method to apply style transfer to pretrained 3DGS scenes. |
Bruno Galerne; Jianling Wang; Lara Raad; Jean-Michel Morel; | arxiv-cs.CV | 2024-12-04 |
| 275 | Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Style3D, a novel approach for generating stylized 3D objects from a content image and a style image. |
Bingjie Song; Xin Huang; Ruting Xie; Xue Wang; Qing Wang; | arxiv-cs.CV | 2024-12-04 |
| 276 | GIST: Towards Photorealistic Style Transfer Via Multiscale Geometric Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Motivated by the ability of multiscale geometric image representations to capture fine-grained details and global structure, we propose GIST: Geometric-based Image Style Transfer, a novel Style Transfer technique that exploits the geometric properties of content and style images. |
Renan A. Rojas-Gomez; Minh N. Do; | arxiv-cs.CV | 2024-12-03 |
| 277 | A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. |
Zhongliang Guo; Weiye Li; Yifei Qian; Ognjen Arandjelovic; Lei Fang; | aistats | 2024-12-01 |
| 278 | Content-activating for Artistic Style Transfer with Ambiguous Sketchy Content Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
YINQI CHEN et. al. | Neurocomputing | 2024-12-01 |
| 279 | Z-STAR+: A Zero-shot Style Transfer Method Via Adjusting Style Distribution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a Cross-attention Reweighting module that utilizes local content features to query style image information best suited to the input patch, thereby aligning the style distribution of the stylized results with that of the style image. |
Yingying Deng; Xiangyu He; Fan Tang; Weiming Dong; | arxiv-cs.CV | 2024-11-28 |
| 280 | Music2Fail: Transfer Music to Failed Recorder Style Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we investigate another style transfer scenario called “failed-music style transfer”. |
CHON IN LEONG et. al. | arxiv-cs.SD | 2024-11-27 |
| 281 | Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities. To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. |
DONGPING CHEN et. al. | arxiv-cs.CV | 2024-11-26 |
| 282 | CapHDR2IR: Caption-Driven Transfer from Visible Light to Infrared Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This occurs when multiple objects with similar temperatures appear indistinguishable in the training data, further exacerbating the loss of fidelity. To solve this challenge, this paper proposes CapHDR2IR, a novel framework incorporating vision-language models using high dynamic range (HDR) images as inputs to generate IR images. |
JINGCHAO PENG et. al. | arxiv-cs.CV | 2024-11-25 |
| 283 | Stylus: Repurposing Stable Diffusion for Training-Free Music Style Transfer on Mel-Spectrograms Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To improve fidelity,we introduce a phase-preserving reconstruction strategy that avoids artifactsfrom Griffin-Lim reconstruction, and we adopt classifier-free-guidance-inspiredcontrol for adjustable stylization and multi-style blending. |
HEEHWAN WANG et. al. | arxiv-cs.SD | 2024-11-24 |
| 284 | Inpainting with Style: Forcing Style Coherence to Image Inpainting with Deep Image Prior Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we combine the deep image prior (DIP) framework with a style transfer (ST) technique to propose a novel approach (called DIP-ST) for image inpainting of artworks. … |
E. Morotti; Fabio Merizzi; Davide Evangelista; Pasquale Cascarano; | Frontiers Comput. Sci. | 2024-11-22 |
| 285 | HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Despite their success, adapting these models to diverse tasks such as domain adaptation, reference-guided synthesis, and text-guided manipulation with limited training data remains challenging. Towards this end, in this study, we present a novel framework that significantly extends the capabilities of a pre-trained StyleGAN by integrating CLIP space via hypernetworks. |
ABDUL BASIT ANEES et. al. | arxiv-cs.CV | 2024-11-19 |
| 286 | MV2MV: Multi-View Image Translation Via View-Consistent Diffusion Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image translation has various applications in computer graphics and computer vision, aiming to transfer images from one domain to another. Thanks to the excellent generation … |
Youcheng Cai; Runshi Li; Ligang Liu; | ACM Trans. Graph. | 2024-11-19 |
| 287 | Towards Multi-View Consistent Style Transfer with One-Step Diffusion Via Vision Conditioning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To efficiently adapt the pre-trained model for multi-view style transfer on small datasets, we introduce a vision condition module to extract style information from the reference style image to serve as conditional input for the diffusion model and employ LoRA in diffusion model for adaptation. |
YUSHEN ZUO et. al. | arxiv-cs.CV | 2024-11-15 |
| 288 | Mechanisms of Generative Image-to-Image Translation Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a streamlined image-to-image translation network with a simpler architecture compared to existing models. |
Guangzong Chen; Mingui Sun; Zhi-Hong Mao; Kangni Liu; Wenyan Jia; | arxiv-cs.CV | 2024-11-15 |
| 289 | Conditional Font Generation With Content Pre‐Train and Style Filter Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Automatic font generation aims to streamline the design process by creating new fonts with minimal style references. This technology significantly reduces the manual labour and … |
Yang Hong; Yinfei Li; Xiaojun Qiao; Junsong Zhang; | Computer Graphics Forum | 2024-11-15 |
| 290 | Artistic Neural Style Transfer Algorithms with Activation Smoothing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we re-implement image-based NST, fast NST, and arbitrary NST. |
XIANGTIAN LI et. al. | arxiv-cs.CV | 2024-11-12 |
| 291 | TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Furthermore, current SVS models often fail to generate singing voices rich in stylistic nuances for unseen singers. To address these challenges, we introduce TCSinger, the first zero-shot SVS model for style transfer across cross-lingual speech and singing styles, along with multi-level style control. |
YU ZHANG et. al. | emnlp | 2024-11-11 |
| 292 | AI-Driven Stylization of 3D Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this system, we discuss methods to stylize a scene of 3D primitive objects into a higher fidelity 3D scene using novel 3D representations like NeRFs and 3D Gaussian Splatting. |
Yuanbo Chen; Yixiao Kang; Yukun Song; Cyrus Vachha; Sining Huang; | arxiv-cs.CV | 2024-11-08 |
| 293 | Diff-TST: Diffusion Model for One-shot Text-image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
SIZHE PANG et. al. | Expert Syst. Appl. | 2024-11-01 |
| 294 | STRAT: Image Style Transfer with Region-aware Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Na Qi; Yezi Li; Rao Fu; Qing Zhu; | Neurocomputing | 2024-11-01 |
| 295 | NCST: Neural-based Color Style Transfer for Video Retouching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Typically, users cannot fine-tune the resulting images or videos. To tackle this issue, we introduce a method that predicts specific parameters for color style transfer using two images. |
Xintao Jiang; Yaosen Chen; Siqin Zhang; Wei Wang; Xuming Wen; | arxiv-cs.CV | 2024-10-31 |
| 296 | FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike existing methods that require either training auxiliary networks or fine-tuning a large pre-trained backbone, or both, to harmonize a foreground object with a painterly-style background image, our FreePIH tames the denoising process as a plug-in module for foreground image style transfer. Specifically, we find that the very last few steps of the denoising (i.e., generation) process strongly correspond to the stylistic information of images, and based on this, we propose to augment the latent features of both the foreground and background images with Gaussians for a direct denoising-based harmonization. |
Ruibin Li; Jingcai Guo; Qihua Zhou; Song Guo; | mm | 2024-10-30 |
| 297 | Learning A Low-Level Vision Generalist Via Visual Task Prompt IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In addition, these methods are sensitive to prompt image content and often struggle with low-frequency information processing. In this paper, we propose a Visual task Prompt-based Image Processing (VPIP) framework to overcome these challenges. |
XIANGYU CHEN et. al. | mm | 2024-10-30 |
| 298 | Uni-DlLoRA: Style Fine-Tuning for Fashion Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods focus on enhancing the generative model with diversity while lacking ID-preserved domain translation. This paper introduces a novel model named Uni-DlLoRA to release this constraint. |
Fangjian Liao; Xingxing Zou; Waikeung Wong; | mm | 2024-10-30 |
| 299 | Dual-head Genre-instance Transformer Network for Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Meichen Liu; Shuting He; Songnan Lin; Bihan Wen; | ACM Multimedia | 2024-10-28 |
| 300 | Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present Kandinsky 3, a novel T2I model based on latent diffusion, achieving a high level of quality and photorealism. |
VLADIMIR ARKHIPKIN et. al. | arxiv-cs.CV | 2024-10-28 |
| 301 | IconDM: Text-Guided Icon Set Expansion Using Diffusion Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Icons are ubiquitous visual elements in graphic design. However, their creation is non-trivial and time-consuming. To this end, we draw inspiration from the booming text-to-image … |
JIAWEI LIN et. al. | ACM Multimedia | 2024-10-28 |
| 302 | Uni-DlLoRA: Style Fine-Tuning for Fashion Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Fangjian Liao; Xingxing Zou; W. Wong; | ACM Multimedia | 2024-10-28 |
| 303 | Improving Real-Time Near-Infrared Face Alignment With A Paired VIS-NIR Dataset and Data Augmentation Through Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Langning Miao; Ryo Kakimoto; Kaoru Ohishi; Yoshihiro Watanabe; | International Conference on Information Photonics | 2024-10-27 |
| 304 | UniVST: A Unified Framework for Training-free Localized Video Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper presents UniVST, a unified framework for localized video style transfer based on diffusion models. |
QUANJIAN SONG et. al. | arxiv-cs.CV | 2024-10-26 |
| 305 | DiffuseST: Unleashing The Capability of The Diffusion Model for Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a novel and training-free approach for style transfer, combining textual embedding with spatial features and separating the injection of content or style. |
Ying Hu; Chenyi Zhuang; Pan Gao; | arxiv-cs.CV | 2024-10-19 |
| 306 | Group Diffusion Transformers Are Unsupervised Multitask Learners IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem. |
LIANGHUA HUANG et. al. | arxiv-cs.CV | 2024-10-19 |
| 307 | SSL-RGB2IR: Semi-supervised RGB-to-IR Image-to-Image Translation for Enhancing Visual Task Training in Semantic Segmentation and Object Detection Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The scarcity of annotated infrared (IR) image datasets limits deep learning networks from achieving performances comparable to those achieved with RGB data. To address this, we … |
Aniruddh Sikdar; Qiranul Saadiyean; Prahlad Anand; Suresh Sundaram; | 2024 IEEE/RSJ International Conference on Intelligent … | 2024-10-14 |
| 308 | 4DStyleGaussian: Zero-shot 4D Style Transfer with Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce 4DStyleGaussian, a novel 4D style transfer framework designed to achieve real-time stylization of arbitrary style references while maintaining reasonable content affinity, multi-view consistency, and temporal coherence. |
Wanlin Liang; Hongbin Xu; Weitao Chen; Feng Xiao; Wenxiong Kang; | arxiv-cs.CV | 2024-10-14 |
| 309 | TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: GAN-based STE methods generally encounter a common issue of model generalization, while Diffusion-based STE methods suffer from undesired style deviations. To address these problems, we propose TextCtrl, a diffusion-based method that edits text with prior guidance control. |
Weichao Zeng; Yan Shu; Zhenhang Li; Dongbao Yang; Yu Zhou; | arxiv-cs.CV | 2024-10-13 |
| 310 | EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel approach termed Exemplar-guided Image Translation with Brownian-Bridge Diffusion Models (EBDM). |
Eungbean Lee; Somi Jeong; Kwanghoon Sohn; | arxiv-cs.CV | 2024-10-13 |
| 311 | TextMaster: A Unified Framework for Realistic Text Editing Via Glyph-Style Dual-Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods,however, face significant limitations in terms of stroke accuracy for complextext and controllability of generated text styles. To address these challenges,we propose TextMaster, a solution capable of accurately editing text acrossvarious scenarios and image regions, while ensuring proper layout andcontrollable text style. |
ZHENYU YAN et. al. | arxiv-cs.CV | 2024-10-13 |
| 312 | Bridging Text and Image for Artist Style Transfer Via Contrastive Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a Contrastive Learning for Artistic Style Transfer (CLAST) that leverages advanced image-text encoders to control arbitrary style transfer. |
Zhi-Song Liu; Li-Wen Wang; Jun Xiao; Vicky Kalogeiton; | arxiv-cs.CV | 2024-10-12 |
| 313 | NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Existing models often fail to maintain sequence temporal consistency, disrupting frame transitions. To tackle this issue, this paper introduces NaRCan, a video editing framework that integrates a hybrid deformation field network with diffusion priors. |
TING-HSUAN CHEN et. al. | nips | 2024-10-07 |
| 314 | Beyond Imperfections: A Conditional Inpainting Approach for End-to-End Artifact Removal in VTON and Pose Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Artifacts often degrade the visual quality of virtual try-on (VTON) and pose transfer applications, impacting user experience. This study introduces a novel conditional inpainting technique designed to detect and remove such distortions, improving image aesthetics. |
Aref Tabatabaei; Zahra Dehghanian; Maryam Amirmazlaghani; | arxiv-cs.CV | 2024-10-05 |
| 315 | PixelShuffler: A Simple Image Translation Through Pixel Rearrangement Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a novel pixel shuffle method that addresses the image-to-image translation problem generally with a specific demonstrative application in style transfer. |
Omar Zamzam; | arxiv-cs.CV | 2024-10-03 |
| 316 | Harnessing The Latent Diffusion Model for Training-Free Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a training-free style transfer algorithm, Style Tracking Reverse Diffusion Process (STRDP) for a pretrained Latent Diffusion Model (LDM). |
Kento Masui; Mayu Otani; Masahiro Nomura; Hideki Nakayama; | arxiv-cs.CV | 2024-10-02 |
| 317 | A Pavement Crack Translator for Data Augmentation and Pixel-Level Detection Based on Weakly Supervised Learning IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent state-of-the-art pavement crack detection algorithms are data-driven and domain-sensitive due to their heavy reliance on datasets. Establishing a high-quality pavement … |
JINGTAO ZHONG et. al. | IEEE Transactions on Intelligent Transportation Systems | 2024-10-01 |
| 318 | Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a pixel-aware stable diffusion (PASD) network to achieve robust Real-ISR and personalized image stylization. |
Tao Yang; Rongyuan Wu; Peiran Ren; Xuansong Xie; Lei Zhang; | eccv | 2024-09-30 |
| 319 | Implicit Style-Content Separation Using B-LoRA IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce B-LoRA, a method that leverages LoRA (Low-Rank Adaptation) to implicitly separate the style and content components of a single image, facilitating various image stylization tasks. |
Yarden Frenkel; Yael Vinker; Ariel Shamir; Danny Cohen-Or; | eccv | 2024-09-30 |
| 320 | LEGO: Learning EGOcentric Action Frame Generation Via Visual Instruction Tuning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a novel problem – egocentric action frame generation. |
BOLIN LAI et. al. | eccv | 2024-09-30 |
| 321 | Revisiting Feature Disentanglement Strategy in Diffusion Training and Breaking Conditional Independence Assumption in Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a training framework for feature disentanglement of Diffusion Models (FDiff). |
WONWOONG CHO et. al. | eccv | 2024-09-30 |
| 322 | WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our work, we leverage an explicit Gaussian Scale (GS) representation and directly match the distributions of Gaussians between style and content scenes using the Earth Mover’s Distance (EMD). |
DMYTRO KOTOVENKO et. al. | eccv | 2024-09-30 |
| 323 | Towards Compact Reversible Image Representations for Neural Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we learn compact neural representations for style transfer motivated from an information theoretical perspective. |
XIYAO LIU et. al. | eccv | 2024-09-30 |
| 324 | InstaStyle: Inversion Noise of A Stylized Image Is Secretly A Style Adviser IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose InstaStyle, a novel approach that excels in generating high-fidelity stylized images with only a single reference image. |
XING CUI et. al. | eccv | 2024-09-30 |
| 325 | WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our work, we leverage an explicit Gaussian Splatting (GS) representation and directly match the distributions of Gaussians between style and content scenes using the Earth Mover’s Distance (EMD). |
DMYTRO KOTOVENKO et. al. | arxiv-cs.CV | 2024-09-26 |
| 326 | Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper proposes Pix2Next, a novel image-to-image translation framework designed to address the challenge of generating high-quality Near-Infrared (NIR) images from RGB inputs. |
YOUNGWAN JIN et. al. | arxiv-cs.CV | 2024-09-25 |
| 327 | Copying Style, Extracting Value: Illustrators’ Perception of AI Style Transfer and Its Impact on Creative Labor Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We provided four illustrators with a model fine-tuned to their style and conducted semi-structured interviews about the model’s successes, limitations, and potential uses. |
Julien Porquet; Sitong Wang; Lydia B. Chilton; | arxiv-cs.HC | 2024-09-25 |
| 328 | AEANet: Affinity Enhanced Attentional Networks for Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing style transfer methods often significantly damage the texture lines of the content image during the style transformation. To address these issues, we propose affinity-enhanced attentional network, which include the content affinity-enhanced attention (CAEA) module, the style affinity-enhanced attention (SAEA) module, and the hybrid attention (HA) module. |
Gen Li; Xianqiu Zheng; Yujian Li; | arxiv-cs.CV | 2024-09-22 |
| 329 | Embedded Image-to-Image Translation for Efficient Sim-to-Real Transfer in Learning-based Robot-Assisted Soft Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel approach utilizing image translation models to mitigate domain mismatches and facilitate efficient robot skill learning in a simulated environment. |
Jacinto Colan; Keisuke Sugita; Ana Davila; Yutaro Yamada; Yasuhisa Hasegawa; | arxiv-cs.RO | 2024-09-16 |
| 330 | Modifying Gesture Style with Impression Words Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: When people form impressions of others in face-to-face communication, gesture style (i.e. the way of gesturing) impacts their impressions, such as being well-mannered, honest, and … |
Jie Zeng; Yoshiki Takahashi; Yukiko I. Nakano; Tatsuya Sakato; H. Vilhjálmsson; | Proceedings of the 24th ACM International Conference on … | 2024-09-16 |
| 331 | Mamba-ST: State Space Model for Efficient Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To overcome the above, this paper explores a novel design of Mamba, an emergent State-Space Model (SSM), called Mamba-ST, to perform style transfer. |
FILIPPO BOTTI et. al. | arxiv-cs.CV | 2024-09-16 |
| 332 | One-Shot Learning for Pose-Guided Person Image Synthesis in The Wild Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, naively applying test-time tuning results in inconsistencies in facial identities and appearance attributes. To address this, we introduce a Visual Consistency Module (VCM), which enhances appearance consistency by combining the face, text, and image embedding. |
DONGQI FAN et. al. | arxiv-cs.CV | 2024-09-14 |
| 333 | MagicStyle: Portrait Stylization Based on Reference Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This challenge becomes even more pronounced when the content image is a portrait which has complex textural details. To address this challenge, we propose a diffusion model-based reference image stylization method specifically for portraits, called MagicStyle. |
Zhaoli Deng; Kaibin Zhou; Fanyi Wang; Zhenpeng Mi; | arxiv-cs.CV | 2024-09-12 |
| 334 | StructuReiser: A Structure-preserving Video Stylization Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce StructuReiser, a novel video-to-video translation method that transforms input videos into stylized sequences using a set of user-provided keyframes. |
Radim Spetlik; David Futschik; Daniel Sykora; | arxiv-cs.CV | 2024-09-09 |
| 335 | MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. |
JIANCHENG HUANG et. al. | arxiv-cs.CV | 2024-09-08 |
| 336 | Seed-to-Seed: Image Translation in Diffusion Seed Space Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Seed-to-Seed Translation (StS), a novel approach for Image-to-Image Translation using diffusion models (DMs), aimed at translations that require close adherence to the structure of the source image. |
Or Greenberg; Eran Kishon; Dani Lischinski; | arxiv-cs.CV | 2024-09-01 |
| 337 | ST2SI: Image Style Transfer Via Vision Transformer Using Spatial Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Wenshu Li; Yinliang Chen; Xiaoying Guo; Xiaoyu He; | Comput. Graph. | 2024-09-01 |
| 338 | Style Transfer: From Stitching to Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This article compares two style transfer methods in image processing: the traditional method, which synthesizes new images by stitching together small patches from existing images, and a modern machine learning-based approach that uses a segmentation network to isolate foreground objects and apply style transfer solely to the background. |
XINHE XU et. al. | arxiv-cs.CV | 2024-09-01 |
| 339 | Universal Dehazing Via Haze Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Single image dehazing has been actively studied to overcome the quality degradation of hazy images. Most of the existing methods take model-based approaches and the existing … |
Eunpil Park; Jaejun Yoo; Jae-Young Sim; | IEEE Transactions on Circuits and Systems for Video … | 2024-09-01 |
| 340 | Cvstgan: A Controllable Generative Adversarial Network for Video Style Transfer of Chinese Painting Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Z. Wang; Fang Liu; Changjuan Ran; | Multim. Syst. | 2024-08-30 |
| 341 | CSGO: Content-Style Composition in Text-to-Image Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we present a data construction pipeline for content-style-stylized image triplets that generates and automatically cleanses stylized data triplets. |
PENG XING et. al. | arxiv-cs.CV | 2024-08-29 |
| 342 | G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields Across Scenes and Styles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we overcome the limitations of existing methods by rendering stylized novel views from a NeRF without the need for per-scene or per-style optimization. |
Adil Meric; Umut Kocasari; Matthias Nießner; Barbara Roessle; | arxiv-cs.CV | 2024-08-24 |
| 343 | Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we provide a comprehensiveanalysis of text embeddings in Stable Diffusion XL, offering three keyinsights: (1) \textit{aug embedding}~\footnote{\textit{aug embedding} isobtained by combining the pooled output of the final text encoder with thetimestep embeddings. |
Yitong Yang; Yinglin Wang; Tian Zhang; Jing Wang; Shuting He; | arxiv-cs.CV | 2024-08-24 |
| 344 | Query-Efficient Video Adversarial Attack with Stylized Logo Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). |
DUOXUN TANG et. al. | arxiv-cs.CV | 2024-08-21 |
| 345 | FAGStyle: Feature Augmentation on Geodesic Surface for Zero-shot Text-guided Diffusion Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite their versatility, these methods often struggle with maintaining style consistency, reflecting the described style accurately, and preserving the content of the target image. To address these challenges, we introduce FAGStyle, a zero-shot text-guided diffusion image style transfer method. |
Yuexing Han; Liheng Ruan; Bing Wang; | arxiv-cs.CV | 2024-08-20 |
| 346 | Structure-preserving Image Translation for Depth Estimation in Colonoscopy Video Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a general pipeline of structure-preserving synthetic-to-real (sim2real) image translation (producing a modified version of the input image) to retain depth geometry through the translation process. |
Shuxian Wang; Akshay Paruchuri; Zhaoxi Zhang; Sarah McGill; Roni Sengupta; | arxiv-cs.CV | 2024-08-19 |
| 347 | StyleBrush: Style Extraction and Transfer from A Single Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose StyleBrush, a method that accurately captures styles from a reference image and “brushes” the extracted style onto other input visual content. |
WANCHENG FENG et. al. | arxiv-cs.CV | 2024-08-18 |
| 348 | The Dawn of KAN in Image-to-Image (I2I) Translation: Integrating Kolmogorov-Arnold Networks with GANs for Unpaired I2I Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This study aims to demonstrate that the Kolmogorov-Arnold Network (KAN) can effectively replace the Multi-layer Perceptron (MLP) method in generative AI, particularly in the subdomain of image-to-image translation, to achieve better generative quality. |
Arpan Mahara; Naphtali D. Rishe; Liangdong Deng; | arxiv-cs.CV | 2024-08-15 |
| 349 | Audio-guided Implicit Neural Representation for Local Image Stylization Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: We present a novel framework for audio-guided localized image stylization. Sound often provides information about the specific context of a scene and is closely related to a … |
SEUNG HYUN LEE et. al. | Comput. Vis. Media | 2024-08-14 |
| 350 | An Analysis for Image-to-Image Translation and Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the development of generative technologies in deep learning, a large number of image-to-image translation and style transfer models have emerged at an explosive rate in … |
Xiaoming Yu; Jie Tian; Zhenhua Hu; | arxiv-cs.CV | 2024-08-12 |
| 351 | Multi-Modal Driven Pose-Controllable Talking Head Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Talking head, driving a source image to generate a talking video using other modality information, has made great progress in recent years. However, there are two main issues: (1) … |
Kuiyuan Sun; Xiaolong Liu; Xiaolong Li; Yao Zhao; Wei Wang; | ACM Transactions on Multimedia Computing, Communications … | 2024-08-10 |
| 352 | InstantStyleGaussian: Efficient Art Style Transfer with 3D Gaussian Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present InstantStyleGaussian, an innovative 3D style transfer method based on the 3D Gaussian Splatting (3DGS) scene representation. |
Xin-Yi Yu; Jun-Xin Yu; Li-Bo Zhou; Yan Wei; Lin-Lin Ou; | arxiv-cs.CV | 2024-08-08 |
| 353 | CLIP-based Point Cloud Classification Via Point Cloud to Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Secondly, the adapter only relies on the global representation of the multi-view features. Motivated by this observation, we propose a Pretrained Point Cloud to Image Translation Network (PPCITNet) that produces generalized colored images along with additional salient visual cues to the point cloud depth maps so that it can achieve promising performance on point cloud classification and understanding. |
Shuvozit Ghose; Manyi Li; Yiming Qian; Yang Wang; | arxiv-cs.CV | 2024-08-07 |
| 354 | D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a novel framework called D$^2$Styler (Discrete Diffusion Styler) that leverages the discrete representational capability of VQ-GANs and the advantages of discrete diffusion, including stable training and avoidance of mode collapse. |
Onkar Susladkar; Gayatri Deshmukh; Sparsh Mittal; Parth Shastri; | arxiv-cs.CV | 2024-08-07 |
| 355 | A Multi-Level Cross-Attention Image Registration Method for Visible and Infrared Small Unmanned Aerial Vehicle Targets Via Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Small UAV target detection and tracking based on cross-modality image fusion have gained widespread attention. Due to the limited feature information available from small UAVs in … |
WEN JIANG et. al. | Remote. Sens. | 2024-08-07 |
| 356 | IPAdapter-Instruct: Resolving Ambiguity in Image-based Conditioning Using Instruct Prompts IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose IPAdapter-Instruct, which combines natural-image conditioning with “Instruct” prompts to swap between interpretations for the same conditioning image: style transfer, object extraction, both, or something else still? |
CIARA ROWLES et. al. | arxiv-cs.CV | 2024-08-06 |
| 357 | FastEdit: Fast Text-Guided Single-Image Editing Via Semantic-Aware Diffusion Fine-Tuning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Conventional Text-guided single-image editing approaches require a two-step process, including fine-tuning the target text embedding for over 1K iterations and the generative … |
Zhi Chen; Zecheng Zhao; Yadan Luo; Zi Huang; | ArXiv | 2024-08-06 |
| 358 | Who Looks Like Me: Semantic Routed Image Harmonization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Image harmonization, aiming to seamlessly blend extraneous foreground objects with background images, is a promising and challenging task.Ensuring a synthetic image appears realistic requires maintaining consistency in visual characteristics, such as texture and style, across global and semantic regions.In this paper, We approach image harmonization as a semantic routed style transfer problem, and propose an imageharmonization model by routing semantic similarity explicitly to enhance the consistency of appearance characteristics.To refine calculate the similarity between the composed foreground and background instance, we propose an InstanceSimilarity Evaluation Module(ISEM). |
JINSHENG SUN et. al. | ijcai | 2024-08-03 |
| 359 | Diffutoon: High-Resolution Editable Toon Shading Via Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we model the toon shading problem as four subproblems, i.e., stylization, consistency enhancement, structure guidance, and colorization. |
Zhongjie Duan; Chengyu Wang; Cen Chen; Weining Qian; Jun Huang; | ijcai | 2024-08-03 |
| 360 | FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper contributesa novel, concise, and efficient approach that adapts pre-trained large-scaletext-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in aplug-and-play manner, realizing high-quality and versatile text-driven I2Itranslation without any model training, model fine-tuning, or onlineoptimization process. |
Xiang Gao; Jiaying Liu; | arxiv-cs.CV | 2024-08-02 |
| 361 | StyleRF-VolVis: Style Transfer of Neural Radiance Fields for Expressive Volume Visualization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces StyleRF-VolVis, an innovative style transfer framework for expressive volume visualization (VolVis) via neural radiance field (NeRF). |
Kaiyuan Tang; Chaoli Wang; | arxiv-cs.GR | 2024-07-31 |
| 362 | Toonify3D: StyleGAN-based 3D Stylized Face Generator Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our goal is to create expressive 3D faces by turning Toonify into a 3D stylized face generator. |
WONJONG JANG et. al. | siggraph | 2024-07-28 |
| 363 | Controllable Neural Style Transfer for Dynamic Meshes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we propose a novel mesh stylization technique that improves previous NST works in several ways. |
Guilherme Gomes Haetinger; Jingwei Tang; Raphael Ortiz; Paul Kanyuk; Vinicius Azevedo; | siggraph | 2024-07-28 |
| 364 | A Deep Learning-based Neural Style Transfer Optimization Approach Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Neural style transfer is used as an optimization technique that combines two different images – a content image and a style reference image – to produce an output image that … |
Priyanshi Sethi; Rhythm Bhardwaj; Nonita Sharma; Deepak Kumar Sharma; Gautam Srivastava; | Intelligent Data Analysis | 2024-07-27 |
| 365 | DiffArtist: Towards Structure and Appearance Controllable Image Stylization Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: Artistic styles are defined by both their structural and appearance elements.Existing neural stylization techniques primarily focus on transferringappearance-level features such … |
Ruixiang Jiang; Changwen Chen; | arxiv-cs.CV | 2024-07-22 |
| 366 | Few-Shot Face Sketch-to-Photo Synthesis Via Global-Local Asymmetric Image-to-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Face sketch-to-photo synthesis is widely used in law enforcement and digital entertainment, which can be achieved by image-to-image (I2I) translation. Traditional I2I translation … |
Yongkang Li; Qifan Liang; Zhen Han; Wenjun Mai; Zhongyuan Wang; | ACM Trans. Multim. Comput. Commun. Appl. | 2024-07-20 |
| 367 | Making Magic with 3D Volume Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In order to achieve the unique look of a hand-drawn, 2D visual style blended with 3D effects elements in Walt Disney Animation Studios’ film Wish, effects artists leveraged new … |
Marie Tollec; Mike Navarro; | ACM SIGGRAPH 2024 Talks | 2024-07-18 |
| 368 | Color-SD: Stable Diffusion Model Already Has A Color Style Noisy Latent Space Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: We present Color-SD, a comprehensive color style transfer framework that utilizes either image or text references. Built on the pretrained Stable Diffusion Model, Color-SD … |
Jiancheng Huang; Mingfu Yan; Yifan Liu; Shifeng Chen; | 2024 IEEE International Conference on Multimedia and Expo … | 2024-07-15 |
| 369 | Photorealistic Image Style Transfer Based on Explicit Affine Transformation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Global or local style transfer often relies on matrix transformations [1], [2], [3], [4] [5]. In any scale of the image feature space, the representation of color can be seen as … |
Junjie Kang; Jinsong Wu; Shiqi Jiang; | 2024 IEEE International Conference on Multimedia and Expo … | 2024-07-15 |
| 370 | StyleSplat: 3D Object Style Transfer with Gaussian Splatting IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce StyleSplat, a lightweight method for stylizing 3D objects in scenes represented by 3D Gaussians from reference style images. |
Sahil Jain; Avik Kuthiala; Prabhdeep Singh Sethi; Prakanshul Saxena; | arxiv-cs.CV | 2024-07-12 |
| 371 | Deep Learning-Powered Optical Microscopy for Steel Research Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The success of machine learning (ML) models in object or pattern recognition naturally leads to ML being employed in the classification of the microstructure of steel surfaces. … |
Š. MIKMEKOVÁ et. al. | Mach. Learn. Knowl. Extr. | 2024-07-11 |
| 372 | MSF: A Multi-Scale Fusion Generative Adversarial Network for SAR-to-Optical Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This paper proposes an image translation method based on multi-scale fusion GAN (MFS) network. In MFS network, there are two modules: optical image generation sub-network (OGS), … |
YONGKANG CHEN et. al. | IGARSS 2024 – 2024 IEEE International Geoscience and Remote … | 2024-07-07 |
| 373 | Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Ada-Adapter, a novel framework for few-shot style personalization of diffusion models. |
JIA LIU et. al. | arxiv-cs.CV | 2024-07-07 |
| 374 | Frequency-Controlled Diffusion Model for Versatile Text-Guided Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper proposes frequency-controlled diffusion model (FCDiffusion), an end-to-end diffusion-based framework that contributes a novel solution to text-guided I2I from a frequency-domain perspective. |
Xiang Gao; Zhengbo Xu; Junhan Zhao; Jiaying Liu; | arxiv-cs.CV | 2024-07-03 |
| 375 | FastFaceCLIP: A Lightweight Text-driven High-quality Face Image Manipulation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Although many new methods have emerged in text‐driven images, the large computational power required for model training causes these methods to have a slow training process. … |
Jiaqi Ren; Junping Qin; Qianli Ma; Yin Cao; | IET Comput. Vis. | 2024-07-02 |
| 376 | Image-to-image Translation Based Face Photo De-meshing Using GANs Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
ABDUL JABBAR et. al. | Comput. Vis. Image Underst. | 2024-07-01 |
| 377 | StyleShot: A Snapshot on Any Style IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. |
JUNYAO GAO et. al. | arxiv-cs.CV | 2024-07-01 |
| 378 | Artistic Style Decomposition for Texture and Shape Editing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: While methods for generative image synthesis and example-based stylization produce impressive results, their black-box style representation intertwines shape, texture, and color … |
M. REIMANN et. al. | The Visual Computer | 2024-07-01 |
| 379 | Expanding The Defect Image Dataset of Composite Material Coating with Enhanced Image-to-image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Xinrui Tao; Hanjun Gao; Kai Yang; Qiong Wu; | Eng. Appl. Artif. Intell. | 2024-07-01 |
| 380 | SwinIT: Hierarchical Image-to-Image Translation Framework Without Cycle Consistency Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-to-image (I2I) translation often requires establishing cycle consistency between the source and the translated images across different domains. However, cycle consistency … |
Jin Liu; Huiyuan Fu; Xin Wang; Huadong Ma; | IEEE Transactions on Circuits and Systems for Video … | 2024-07-01 |
| 381 | CHDNet: Enhanced Arbitrary Style Transfer Via Condition Harmony DiffusionNet Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Arbitrary Style Transfer (AST) renders an image by adopting the style of any chosen artwork while preserving its content structure. Despite the widespread popularity of … |
Wenkai He; J. Zhao; Ying Fang; | 2024 International Joint Conference on Neural Networks … | 2024-06-30 |
| 382 | InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To address these challenges, we deconstruct the style transfer task into three core elements: 1) Style, focusing on the image’s aesthetic characteristics; 2) Spatial Structure, concerning the geometric arrangement and composition of visual elements; and 3) Semantic Content, which captures the conceptual meaning of the image. Guided by these principles, we introduce InstantStyle-Plus, an approach that prioritizes the integrity of the original content while seamlessly integrating the target style. |
HAOFAN WANG et. al. | arxiv-cs.CV | 2024-06-30 |
| 383 | MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We train a model to generate images from multimodal prompts of interleaved text and images such as a |
William Berman; Alexander Peysakhovich; | arxiv-cs.CV | 2024-06-26 |
| 384 | Conditional Face Image Manipulation Detection: Combining Algorithm and Human Examiner Decisions Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: It has been shown that digitally manipulated face images can pose a security threat to automated authentication systems (e.g., when such systems are used for border control). In … |
M. IBSEN et. al. | Proceedings of the 2024 ACM Workshop on Information Hiding … | 2024-06-24 |
| 385 | Enhancing Brain MRI Images: Using DC GAN And WGAN For Image Augmentation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Generating and detecting MRI images are most beneficial if the illness requires a fast and accurate cure. Concerning the weakness, there have been negative remarks made about DL … |
MOHAMMAD ABDULLA et. al. | 2024 15th International Conference on Computing … | 2024-06-24 |
| 386 | Artistic Style Transfer Based on Attention with Knowledge Distillation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Artistic style transfer involves the adaption of an input image to reflect the style of a reference image while maintaining its original content. This technique, now a prominent … |
Hanadi Al-Mekhlafi; Shiguang Liu; | Computer Graphics Forum | 2024-06-21 |
| 387 | TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce TinyStyler, a lightweight but effective approach, which leverages a small language model (800M params) and pre-trained authorship embeddings to perform efficient, few-shot text style transfer. |
ZACHARY HORVITZ et. al. | arxiv-cs.CL | 2024-06-21 |
| 388 | Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models. |
Haruo Fujiwara; Yusuke Mukuta; Tatsuya Harada; | arxiv-cs.CV | 2024-06-19 |
| 389 | SDNIA-YOLO: A Robust Object Detection Model for Extreme Weather Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study thus proposes a stylization data-driven neural-image-adaptive YOLO (SDNIA-YOLO), which improves the model’s robustness by enhancing image quality adaptively and learning valuable information related to extreme weather conditions from images synthesized by neural style transfer (NST). |
Yuexiong Ding; Xiaowei Luo; | arxiv-cs.CV | 2024-06-18 |
| 390 | Style Transfer for 2D Talking Head Generation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Audio-driven talking head animation is a challenging research topic with many real-world applications. Recent works have focused on creating photo-realistic 2D animation, while … |
TRONG-THANG PHAM et. al. | 2024 IEEE/CVF Conference on Computer Vision and Pattern … | 2024-06-17 |
| 391 | Domain Targeted Synthetic Plant Style Transfer Using Stable Diffusion, LoRA and ControlNet IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Synthetic images can help alleviate much of the cost in the creation of training data for plant phenotyping-focused AI development. Synthetic-to-real style transfer is of … |
Zane K. J. Hartley; Rob J. Lind; Michael P. Pound; Andrew P. French; | 2024 IEEE/CVF Conference on Computer Vision and Pattern … | 2024-06-17 |
| 392 | DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To provide consistent and controllable editing we propose the image-based video-NeRF editing pipeline with a set of innovative designs including multi-view multi-pose Score Distillation Sampling (SDS) from both the 2D personalized diffusion prior and 3D diffusion prior reconstruction losses text-guided local parts super-resolution and style transfer. |
JIA-WEI LIU et. al. | cvpr | 2024-06-13 |
| 393 | 3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we make a connection between the two and tackle the challenging task of 3D portrait stylization – modeling high-fidelity 3D stylized avatars from captured 2D portrait images. |
YIFANG MEN et. al. | cvpr | 2024-06-13 |
| 394 | Doubly Abductive Counterfactual Inference for Text-based Image Editing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To this end we propose a Doubly Abductive Counterfactual inference framework (DAC). |
XUE SONG et. al. | cvpr | 2024-06-13 |
| 395 | Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we ask the question of whether any 2D vision model can be lifted to make 3D consistent predictions. |
MUKUND VARMA T et. al. | cvpr | 2024-06-13 |
| 396 | Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: For instance it is difficult for CNN-based methods to handle global information and long-range dependencies between input images for which transformer-based methods have been proposed. |
Sizhe Zheng; Pan Gao; Peng Zhou; Jie Qin; | cvpr | 2024-06-13 |
| 397 | Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Despite the impressive generative capabilities of diffusion models existing diffusion model-based style transfer methods require inference-stage optimization (e.g. fine-tuning or textual inversion of style) which is time-consuming or fails to leverage the generative ability of large-scale diffusion models. To address these issues we introduce a novel artistic style transfer method based on a pre-trained large-scale diffusion model without any optimization. |
Jiwoo Chung; Sangeek Hyun; Jae-Pil Heo; | cvpr | 2024-06-13 |
| 398 | Video Prediction By Modeling Videos As Continuous Multi-Dimensional Processes IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In our paper we introduce a novel model class that treats video as a continuous multi-dimensional process rather than a series of discrete frames. |
Gaurav Shrivastava; Abhinav Shrivastava; | cvpr | 2024-06-13 |
| 399 | S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current 3D stylization methods often assume static scenes which violates the dynamic nature of our real world. To address this limitation we present S-DyRF a reference-based spatio-temporal stylization method for dynamic neural radiance fields. |
XINGYI LI et. al. | cvpr | 2024-06-13 |
| 400 | Z*: Zero-shot Style Transfer Via Attention Reweighting IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We further reveal that the cross-attention mechanism in latent diffusion models tends to blend the content and style images resulting in stylized outputs that deviate from the original content image. To overcome this limitation we introduce a cross-attention reweighting strategy. |
Yingying Deng; Xiangyu He; Fan Tang; Weiming Dong; | cvpr | 2024-06-13 |
| 401 | ConIS: Controllable Text-driven Image Stylization with Semantic Intensity Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Gaoming Yang; Changgeng Li; Ji Zhang; | Multim. Syst. | 2024-06-13 |
| 402 | ArtAdapter: Text-to-Image Style Transfer Using Multi-Level Style Encoder and Explicit Adaptation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces ArtAdapter a transformative text-to-image (T2I) style transfer framework that transcends traditional limitations of color brushstrokes and object shape capturing high-level style elements such as composition and distinctive artistic expression. |
Dar-Yen Chen; Hamish Tennent; Ching-Wen Hsu; | cvpr | 2024-06-13 |
| 403 | Misalignment-Robust Frequency Distribution Loss for Image Transformation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper aims to address a common challenge in deep learning-based image transformation methods such as image enhancement and super-resolution which heavily rely on precisely aligned paired datasets with pixel-level alignments. |
ZHANGKAI NI et. al. | cvpr | 2024-06-13 |
| 404 | One-Shot Structure-Aware Stylized Image Synthesis IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Recently diffusion models have been adopted for image stylization but still lack the capability to maintain the original quality of input images. Building on this we propose OSASIS: a novel one-shot stylization method that is robust in structure preservation. |
Hansam Cho; Jonghyun Lee; Seunggyu Chang; Yonghyun Jeong; | cvpr | 2024-06-13 |
| 405 | ICE-G: Image Conditional Editing of 3D Gaussian Splats IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a novel approach to quickly edit a 3D model from a single reference view. |
VISHNU JAGANATHAN et. al. | arxiv-cs.CV | 2024-06-12 |
| 406 | TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: (2) They routinely lead to quality degradation for generation, especially in text-image alignment. This paper proposes a novel training-efficient Latent Consistency Model (TLCM) to overcome these challenges. |
Qingsong Xie; Zhenyi Liao; Zhijie Deng; Chen chen; Haonan Lu; | arxiv-cs.CV | 2024-06-09 |
| 407 | Varying Manifolds in Diffusion: From Time-varying Geometries to Visual Saliency Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep generative models learn the data distribution, which is concentrated on a low-dimensional manifold. The geometric analysis of distribution transformation provides a better … |
Junhao Chen; Manyi Li; Zherong Pan; Xifeng Gao; Changhe Tu; | ArXiv | 2024-06-07 |
| 408 | Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a method to generate 3D objects in styles. |
Hubert Kompanowski; Binh-Son Hua; | arxiv-cs.CV | 2024-06-05 |
| 409 | Graphic Style Transfer Technology in Multimedia Communication: An Application of Deep Residual Adaptive Networks in Graphic Design Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the rapid development of wireless network technology and the rapid popularity of portable smart terminals, multimedia communication based on images and videos has become the … |
Zhenyu Zhang; Fuyu Wei; Guizhen Liang; Xintong Wang; | Int. J. Commun. Networks Inf. Secur. | 2024-06-04 |
| 410 | Application of An Improved U-Net with Image-to-image Translation and Transfer Learning in Peach Orchard Segmentation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
JIAYU CHENG et. al. | Int. J. Appl. Earth Obs. Geoinformation | 2024-06-01 |
| 411 | MegActor: Harness The Power of Raw Video for Vivid Portrait Animation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Despite raw driving videos contain richer information on facial expressions than intermediate representations such as landmarks in the field of portrait animation, they are seldom the subject of research. |
SHURONG YANG et. al. | arxiv-cs.CV | 2024-05-31 |
| 412 | ExpoGenius: Robust Personalized Human Image Generation Using Diffusion Model for Exposure Variation and Pose Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Diffusion models hold significant appeal within the realm of synthetic media generation and demonstrate exceptional performance in personalized human image generation. However, … |
Depei Liu; Hongjie Fan; Junfei Liu; | Proceedings of the 2024 International Conference on … | 2024-05-30 |
| 413 | Analyzing The Impact of Geospatial Derivatives on Domain Adaptation with CycleGAN Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: CycleGAN, a deep learning model for image conversion tasks is an extension of the Pix2Pix architecture [1] offering cycle consistency loss that offers image-to-image translation … |
PAPIA F. ROZARIO et. al. | 2024 IEEE International Conference on Electro Information … | 2024-05-30 |
| 414 | Multi-Step Unsupervised Domain Adaptation in Image and Feature Space for Synthetic Aperture Radar Image Terrain Classification Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The significant differences in data domains between SAR images and the expensive and time-consuming process of data labeling pose significant challenges to terrain classification. … |
ZHONGLE REN et. al. | Remote. Sens. | 2024-05-25 |
| 415 | LEAST: Local Text-conditioned Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we evaluate the text-conditioned image editing and style transfer techniques on their fine-grained understanding of user prompts for precise local style transfer. |
Silky Singh; Surgan Jandial; Simra Shahid; Abhinav Java; | arxiv-cs.CV | 2024-05-25 |
| 416 | Axial Attention Transformer for Fast High-quality Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image style transfer aims to blend the content of one image with the style of another. Due to the limitation of traditional Convolutional Neural Network (CNN) methods in capturing … |
Yuxin Liu; Wenxin Yu; Zhiqiang Zhang; Qi Wang; Lu Che; | 2024 IEEE International Symposium on Circuits and Systems … | 2024-05-19 |
| 417 | HDMA-CGAN: Advancing Image Style Transfer with Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Huaqun Liu; Benxi Hu; Yu Cao; | Int. J. Pattern Recognit. Artif. Intell. | 2024-05-17 |
| 418 | Personalizing Products with Stylized Head Portraits for Self-Expression Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Personalizing products aesthetically or functionally can help users increase personal relevance and support self-expression. However, using non-abstract personal data such as head … |
Yang Shi; Yechun Peng; Shengqi Dang; Nanxuan Zhao; Nan Cao; | Proceedings of the CHI Conference on Human Factors in … | 2024-05-11 |
| 419 | Empathy Through Aesthetics: Using AI Stylization for Visual Anonymization of Interview Videos Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Faces are the primary source for identifying individuals, which need to be obstructed to achieve anonymization in images and videos. However, human faces are also one of the most … |
Ö. Yalçın; Vanessa Utz; Steve Dipaola; | Proceedings of the 3rd Empathy-Centric Design Workshop: … | 2024-05-11 |
| 420 | Analyzing The Application and Key Factors of CycleGAN in Style Transfer Between Chinese Ink Paintings and Van Gogh’s Artworks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Early image style transfer algorithms heavily relied on strict image pairing between target and source domains, which is highly challenging in practice. Algorithms that do not … |
Ningnan Guo; | Proceedings of the 2024 International Conference on … | 2024-05-10 |
| 421 | StyleMamba : State Space Model for Efficient Text-driven Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present StyleMamba, an efficient image style transfer framework that translates text prompts into corresponding visual styles while preserving the content integrity of the original images. |
Zijia Wang; Zhi-Song Liu; | arxiv-cs.CV | 2024-05-08 |
| 422 | SMCD: High Realism Motion Style Transfer Via Mamba-based Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, when handling long-range motion sequences, these methods fail to effectively learn temporal dependencies, ultimately resulting in unnatural generated motions. To address these limitations, we propose a Unified Motion Style Diffusion (UMSD) framework, which simultaneously extracts features from both content and style motions and facilitates sufficient information interaction. |
ZIYUN QIAN et. al. | arxiv-cs.CV | 2024-05-05 |
| 423 | MA-GAN: The Style Transfer Model Based on Multi-adaptive Generative Adversarial Networks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Abstract. Existing style transfer methods need more texture structure of style images with aesthetic guidance, resulting in the loss of a large amount of texture details, which … |
Min Zhao; Xuezhong Qian; Wei Song; | Journal of Electronic Imaging | 2024-05-01 |
| 424 | Stylize My Wrinkles: Bridging The Gap from Simulation to Reality Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Modeling realistic human skin with pores and wrinkles down to the milli‐ and micrometer resolution is a challenging task. Prior work showed that such micro geometry can be … |
Sebastian Weiss; Jackson Stanhope; Prashanth Chandran; Gaspard Zoss; Derek Bradley; | Computer Graphics Forum | 2024-05-01 |
| 425 | DIVIDE: Learning A Domain-Invariant Geometric Space for Depth Estimation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Learning-based depth estimation requires a large amount of real-world training data, which can be both expensive and time-consuming to acquire. As a result, utilizing … |
D. Shim; Ieee H. Jin Kim Member; | IEEE Robotics and Automation Letters | 2024-05-01 |
| 426 | TridentCap: Image-Fact-Style Trident Semantic Framework for Stylized Image Captioning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Stylized image captioning (SIC) aims to generate captions with target style for images. The biggest challenge is that the collection and annotation of stylized data are pretty … |
LANXIAO WANG et. al. | IEEE Transactions on Circuits and Systems for Video … | 2024-05-01 |
| 427 | GAN‐Based Multi‐Decomposition Photo Cartoonization IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Cartoon images play a vital role in film production, scientific and educational animation, video games, and other fields, and are one of the key visual expressions of artistic … |
Wenqing Zhao; Jianlin Zhu; Jin Huang; Ping Li; Bin Sheng; | Computer Animation and Virtual Worlds | 2024-05-01 |
| 428 | NNST-based Image Outpainting Via SinGAN Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The restoration process can be further categorized into image inpainting and outpainting depending on the extent of the damage. Image inpainting is utilized when only a few parts … |
Ryuto Sugahara; Weiwei Du; | Proceedings of the 2024 10th International Conference on … | 2024-04-26 |
| 429 | SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Though a wide range of I2I models tackle this problem, a notable challenge is that the content details of the source image could be easily erased or corrupted due to the transfer of ink-wash style elements. To remedy this issue, we propose to incorporate saliency detection into the unpaired I2I framework to regularize image content, where the detected saliency map is utilized from two aspects: (\romannumeral1) we propose saliency IOU (SIOU) loss to explicitly regularize object content structure by enforcing saliency consistency before and after image stylization; (\romannumeral2) we propose saliency adaptive normalization (SANorm) which implicitly enhances object structure integrity of the generated paintings by dynamically injecting image saliency information into the generator to guide stylization process. |
Xiang Gao; Yuqi Zhang; | arxiv-cs.CV | 2024-04-24 |
| 430 | CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. |
Deheng Zhang; Clara Fernandez-Labrador; Christopher Schroers; | arxiv-cs.CV | 2024-04-23 |
| 431 | Music Style Transfer With Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The existing music style transfer methods generate spectrograms with artifacts, leading to significant noise in the generated audio. To address these issues, this study proposes a music style transfer framework based on diffusion models (DM) and uses spectrogram-based methods to achieve multi-to-multi music style transfer. |
Hong Huang; Yuyi Wang; Luyao Li; Jun Lin; | arxiv-cs.SD | 2024-04-23 |
| 432 | Regional Style and Color Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods often suffer from the drawback of applying style homogeneously across the entire image, leading to stylistic inconsistencies or foreground object twisted when applied to image with foreground elements such as person figures. To address this limitation, we propose a new approach that leverages a segmentation network to precisely isolate foreground objects within the input image. |
Zhicheng Ding; Panfeng Li; Qikai Yang; Siyang Li; Qingtian Gong; | arxiv-cs.CV | 2024-04-22 |
| 433 | Rethink Arbitrary Style Transfer with Transformer and Contrastive Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce an innovative technique to improve the quality of stylized images. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2024-04-21 |
| 434 | Towards Highly Realistic Artistic Style Transfer Via Stable Diffusion with Step-aware and Layer-aware Prompt IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, diffusion model-based methods generally fail to preserve the content structure of input content images well, introducing some undesired content structure and style patterns. To address the above problems, we propose a novel pre-trained diffusion-based artistic style transfer method, called LSAST, which can generate highly realistic artistic stylized images while preserving the content structure of input content images well, without bringing obvious artifacts and disharmonious style patterns. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2024-04-17 |
| 435 | Paste and Harmonize Via Denoising: Subject-Driven Image Editing with Frozen Pre-Trained Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods still face difficulties in exemplar-guided image editing without destroying the given objects’ identity in the exemplar image. To address this problem, we propose a new framework called Paste and Harmonize via Denoising, which leverages pre-trained diffusion models to facilitate the text-driven transfer of objects from an exemplar image to the edited image while preserving their appearance and characteristics. |
X. Zhang; J. Guo; P. Yoo; Y. Matsuo; Y. Iwasawa; | icassp | 2024-04-15 |
| 436 | Lighting Image/Video Style Transfer Methods By Iterative Channel Pruning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Deploying style transfer methods on resource-constrained devices is challenging, which limits their real-world applicability. To tackle this issue, we propose using pruning techniques to accelerate various visual style transfer methods. |
K. Wu; | icassp | 2024-04-15 |
| 437 | Improved Object-Based Style Transfer with Single Deep Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This research paper proposes a novel methodology for image-to-image style transfer on objects utilizing a single deep convolutional neural network. |
Harshmohan Kulkarni; Om Khare; Ninad Barve; Sunil Mane; | arxiv-cs.CV | 2024-04-15 |
| 438 | Instant Photorealistic Neural Radiance Fields Stylization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present Instant Photorealistic Neural Radiance Fields Stylization, a novel approach for multi-view image stylization for the 3D scene. |
S. Li; Y. Pan; | icassp | 2024-04-15 |
| 439 | CReStyler: Text-Guided Single Image Style Transfer Method Based on CNN and Restormer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing text-guided style transfer method suffers from content information missing and artifacts in the generated stylized images. Therefore, we propose CReStyler, a text-guided image style method based on the dual-branch structure of CNN and Restormer. |
L. FENG et. al. | icassp | 2024-04-15 |
| 440 | Arbitrary Style Transfer with Prototype-Based Channel Alignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite the appealing results achieved by existing methods, few studies have considered the alignment of semantics or structures between the style image and the content image. To overcome this problem, we propose a novel network with two parallel branches: coarse-grained stylization branch and fine-grained decoration branch. |
Y. Hong; L. Niu; J. Zhang; | icassp | 2024-04-15 |
| 441 | Arbitrary Style Transfer Based on Content Integrity and Style Consistency Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Thus, a framework of Content Integrity and Style Consistency preserving arbitrary style transfer (CISC-ST) is proposed, which consists of a Dual Style Attention (DSA) mechanism and Frequency Domain Enhancement (FDE) architecture. |
L. Kang; G. Xiao; M. S. Lew; S. Wu; | icassp | 2024-04-15 |
| 442 | Arbitrary Style Transfer Based on Content Integrity and Style Consistency Enhancement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The existing arbitrary style transfer methods mainly suffer two challenges. One is content integrity, as most methods focus too much on style, resulting in incomplete content … |
Lu Kang; Guoqiang Xiao; Michael S. Lew; Song Wu; | ICASSP 2024 – 2024 IEEE International Conference on … | 2024-04-14 |
| 443 | Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. |
YANQI GE et. al. | arxiv-cs.CV | 2024-04-10 |
| 444 | StylizedGS: Controllable Stylization for 3D Gaussian Splatting IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Additionally, the ability for artists to apply flexible control over stylized scenes is considered highly desirable to foster an environment conducive to creative exploration. To address the above issues, we introduce StylizedGS, an efficient 3D neural style transfer framework with adaptable control over perceptual factors based on 3D Gaussian Splatting (3DGS) representation. |
DINGXI ZHANG et. al. | arxiv-cs.CV | 2024-04-08 |
| 445 | Stylizing Sparse-View 3D Scenes with Hierarchical Neural Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we consider the stylization of sparse-view scenes in terms of disentangling content semantics and style textures. |
Y. Wang; A. Gao; Y. Gong; Y. Zeng; | arxiv-cs.CV | 2024-04-08 |
| 446 | RoNet: Rotation-oriented Continuous Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel rotation-oriented solution and model the continuous generation with an in-plane rotation over the style representation of an image, achieving a network named RoNet. |
Yi Li; Xin Xie; Lina Lei; Haiyan Fu; Yanqing Guo; | arxiv-cs.CV | 2024-04-05 |
| 447 | Multi-Domain Image-to-Image Translation with Cross-Granularity Contrastive Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The objective of multi-domain image-to-image translation is to learn the mapping from a source domain to a target domain in multiple image domains while preserving the content … |
Huiyuan Fu; Jin Liu; Tingyi Yu; Xin Wang; Huadong Ma; | ACM Transactions on Multimedia Computing, Communications … | 2024-04-04 |
| 448 | Grid Diffusion Models for Text-to-Video Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These methods require large datasets and are limited in terms of computational costs compared to text-to-image generation. To tackle these challenges, we propose a simple but effective novel grid diffusion for text-to-video generation without temporal dimension in architecture and a large text-video paired dataset. |
Taegyeong Lee; Soyeong Kwon; Taehwan Kim; | arxiv-cs.CV | 2024-03-29 |
| 449 | DiffStyler: Diffusion-based Localized Image Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Recent developments in large-scale text-to-image diffusion models have heralded unprecedented synthesis capabilities, albeit at the expense of relying on extensive and often imprecise textual descriptions to delineate artistic styles. Addressing these limitations, this paper introduces DiffStyler, a novel approach that facilitates efficient and precise arbitrary image style transfer. |
Shaoxu Li; | arxiv-cs.CV | 2024-03-27 |
| 450 | Enhancing Cross-Dataset EEG Emotion Recognition: A Novel Approach with Emotional EEG Style Transfer Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To tackle the significant inter-domain differences in cross-dataset EEG emotion recognition, this paper introduces an innovative solution known as the Emotional EEG Style Transfer Network (E$^2$STN). |
YIJIN ZHOU et. al. | arxiv-cs.HC | 2024-03-25 |
| 451 | DNIT: Enhancing Day-Night Image-to-Image Translation Through Fine-Grained Feature Handling (Student Abstract) Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Existing image-to-image translation methods perform less satisfactorily in the day-night domain due to insufficient scene feature study. To address this problem, we propose … |
Hanyue Liu; Haonan Cheng; L. Ye; | AAAI Conference on Artificial Intelligence | 2024-03-24 |
| 452 | Scaled Aggregation Operations Over Three-dimensional Extended Intuitionistic Fuzzy Index Matrices Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Modern image processing techniques are improving beyond old methods, which include advanced approaches, for example deep learning. Convolutional Neural Networks (CNNs) are … |
Xiaolong Shi; Saeed Kosari; Rangasamy Parvathi; R. K. Nivedhaa; Hossein Rashmanlou; | Journal of Intelligent & Fuzzy Systems | 2024-03-24 |
| 453 | AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Furthermore, these methods frequently rely on textual input as the editing guidance, leading to ambiguities and limiting the types of edits they can perform. Recognizing these challenges, we introduce AnyV2V, a novel tuning-free paradigm designed to simplify video editing into two primary steps: (1) employing an off-the-shelf image editing model to modify the first frame, (2) utilizing an existing image-to-video generation model to generate the edited video through temporal feature injection. |
Max Ku; Cong Wei; Weiming Ren; Harry Yang; Wenhu Chen; | arxiv-cs.CV | 2024-03-21 |
| 454 | Implicit Style-Content Separation Using B-LoRA IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce B-LoRA, a method that leverages LoRA (Low-Rank Adaptation) to implicitly separate the style and content components of a single image, facilitating various image stylization tasks. |
Yarden Frenkel; Yael Vinker; Ariel Shamir; Daniel Cohen-Or; | arxiv-cs.CV | 2024-03-21 |
| 455 | Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities. |
Qianyu Guo; Jiaming Fu; Yawen Lu; Dongming Gan; | arxiv-cs.CV | 2024-03-21 |
| 456 | Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present novel approaches involving generative adversarial networks and diffusion models in order to synthesize high quality, live and spoof fingerprint images while preserving features such as uniqueness and diversity. |
W. Tang; D. Figueroa; D. Liu; K. Johnsson; A. Sopasakis; | arxiv-cs.CV | 2024-03-20 |
| 457 | Diffusion-based Human Motion Style Transfer with Semantic Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, we may encounter a single unseen style example in practical scenarios, but not in sufficient quantity to constitute a style cluster for AdaIN-based methods. Therefore, in this paper, we propose a novel two-stage framework for few-shot style transfer learning based on the diffusion model. |
Lei Hu; Zihao Zhang; Yongjing Ye; Yiwen Xu; Shihong Xia; | arxiv-cs.GR | 2024-03-20 |
| 458 | Diffusion‐based Human Motion Style Transfer with Semantic Guidance Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: 3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN‐based methods necessitate datasets with balanced style … |
Lei Hu; Zihao Zhang; Yongjing Ye; Yiwen Xu; Shihong Xia; | Computer Graphics Forum | 2024-03-20 |
| 459 | LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To close the gap, we propose LocalStyleFool, an improved black-box video adversarial attack that superimposes regional style-transfer-based perturbations on videos. |
YUXIN CAO et. al. | arxiv-cs.CV | 2024-03-18 |
| 460 | Sim2Real Within 5 Minutes: Efficient Domain Transfer with Stylized Gaussian Splatting for Endoscopic Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes an efficient domain transfer method based on stylized Gaussian splatting, only requiring a few of real images (10 images) with very fast training time. |
Junyang Wu; Yun Gu; Guang-Zhong Yang; | arxiv-cs.CV | 2024-03-16 |
| 461 | Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Given that many deterministic conditional image generative models have been able to produce high-quality yet fixed results, we raise an intriguing question: is it possible for pre-trained deterministic conditional image generative models to generate diverse results without changing network structures or parameters? To answer this question, we re-examine the conditional image generation tasks from the perspective of adversarial attack and propose a simple and efficient plug-in projected gradient descent (PGD) like method for diverse and controllable image generation. |
TIANYI CHU et. al. | arxiv-cs.CV | 2024-03-13 |
| 462 | Gaussian Splatting in Style IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In contrast, we propose a novel architecture trained on a collection of style images that, at test time, produces real time high-quality stylized novel views. |
ABHISHEK SAROHA et. al. | arxiv-cs.CV | 2024-03-13 |
| 463 | StyleDyRF: Zero-shot 4D Style Transfer for Dynamic Neural Radiance Fields Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce StyleDyRF, a method that represents the 4D feature space by deforming a canonical feature volume and learns a linear style transformation matrix on the feature volume in a data-driven fashion. |
Hongbin Xu; Weitao Chen; Feng Xiao; Baigui Sun; Wenxiong Kang; | arxiv-cs.CV | 2024-03-13 |
| 464 | Style-Driven Image Enhancement for Entry-Level Mobile Devices Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Modern smartphones usually have automatic camera adjustment features that predetermine how images will be processed. Without an intervention from the user (e.g., manual adjustment … |
Angelo Christian Matias; Neil Patrick Del Gallego; | Proceedings of the 2024 7th International Conference on … | 2024-03-12 |
| 465 | StyleGaussian: Instant 3D Style Transfer with Gaussian Splatting IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce StyleGaussian, a novel 3D style transfer technique that allows instant transfer of any image’s style to a 3D scene at 10 frames per second (fps). |
KUNHAO LIU et. al. | arxiv-cs.CV | 2024-03-12 |
| 466 | Authorship Style Transfer with Policy Optimization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a simple two-stage tune-and-optimize technique for low-resource textual style transfer. |
Shuai Liu; Shantanu Agarwal; Jonathan May; | arxiv-cs.CL | 2024-03-12 |
| 467 | Towards Model Extraction Attacks in GAN-Based Image Translation Via Domain Shift Mitigation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a … |
DI MI et. al. | arxiv-cs.CR | 2024-03-12 |
| 468 | 3D-aware Image Generation and Editing with Multi-modal Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel end-to-end 3D-aware image generation and editing model incorporating multiple types of conditional inputs, including pure noise, text and reference image. |
Bo Li; Yi-ke Li; Zhi-fen He; Bin Liu; Yun-Kun Lai; | arxiv-cs.CV | 2024-03-11 |
| 469 | A Spatiotemporal Style Transfer Algorithm for Dynamic Visual Stimulus Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we introduce the Spatiotemporal Style Transfer (STST) algorithm, a dynamic visual stimulus generation framework that allows powerful manipulation and synthesis of video stimuli for vision research. |
Antonino Greco; Markus Siegel; | arxiv-cs.CV | 2024-03-07 |
| 470 | Conditional Image Hiding Network Based on Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
FENGHUA ZHANG et. al. | Inf. Sci. | 2024-03-01 |
| 471 | Foreground and Background Separated Image Style Transfer with A Single Text Condition Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Yue Yu; Jianming Wang; Nengli Li; | Image Vis. Comput. | 2024-03-01 |
| 472 | Structure Preserving Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper focuses on structure-preserving diffusion models (SPDM), a specific subset of diffusion processes tailored for distributions with inherent structures, such as group symmetries. |
Haoye Lu; Spencer Szabados; Yaoliang Yu; | arxiv-cs.LG | 2024-02-29 |
| 473 | On The Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our contributions include connecting $f$-divergence and score matching, unveiling insights into the impact of Gaussian noise on aligning probability distributions, and demonstrating generalized robustness implications. |
CHAOHUA SHI et. al. | iclr | 2024-02-26 |
| 474 | Ground-A-Video: Zero-shot Grounded Video Editing Using Text-to-image Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper introduces a novel grounding-guided video-to-video translation framework called Ground-A-Video for multi-attribute video editing. |
Hyeonho Jeong; Jong Chul Ye; | iclr | 2024-02-26 |
| 475 | TOSS: High-quality Text-guided Novel View Synthesis from A Single Image IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image. |
YUKAI SHI et. al. | iclr | 2024-02-26 |
| 476 | Image Translation As Diffusion Visual Programmers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. |
CHENG HAN et. al. | iclr | 2024-02-26 |
| 477 | Guiding Instruction-based Image Editing Via Multimodal Large Language Models IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs. |
TSU-JUI FU et. al. | iclr | 2024-02-26 |
| 478 | IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This raises a question: Why does the contrastive learning paradigm not yield satisfactory results in image restoration? In this paper, we conduct in-depth analyses and propose three guidelines to address the above question. |
Dongqi Fan; Xin Zhao; Liang Chang; | arxiv-cs.CV | 2024-02-24 |
| 479 | Music Style Transfer with Time-Varying Inversion of Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper presents a music style transfer approach that effectively captures musical attributes using minimal data. |
SIFEI LI et. al. | arxiv-cs.SD | 2024-02-21 |
| 480 | ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods, including color style transfer and image harmonization, exhibit inconsistencies, especially at boundary regions. Addressing this, we present ChromaFusionNet (CFNet), a novel approach that views the color fusion problem through the lens of image color inpainting. |
YI DONG et. al. | aaai | 2024-02-20 |
| 481 | DreamStyler: Paint By Style Inversion with Text-to-Image Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce DreamStyle, a novel framework designed for artistic image synthesis, proficient in both text-to-image synthesis and style transfer. |
NAMHYUK AHN et. al. | aaai | 2024-02-20 |
| 482 | BARET: Balanced Attention Based Real Image Editing Driven By Target-Text Inversion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Image editing approaches with diffusion models have been rapidly developed, yet their applicability are subject to requirements such as specific editing types (e.g., foreground or background object editing, style transfer), multiple conditions (e.g., mask, sketch, caption), and time consuming fine-tuning of diffusion models. For alleviating these limitations and realizing efficient real image editing, we propose a novel editing technique that only requires an input image and target text for various editing types including non-rigid edits without fine-tuning diffusion model. |
YUMING QIAO et. al. | aaai | 2024-02-20 |
| 483 | FontDiffuser: One-Shot Font Generation Via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Although existing font generation methods have achieved satisfactory performance, they still struggle with complex characters and large style variations. To address these issues, we propose FontDiffuser, a diffusion-based image-to-image one-shot font generation method, which innovatively models the font imitation task as a noise-to-denoise paradigm. |
ZHENHUA YANG et. al. | aaai | 2024-02-20 |
| 484 | HyperEditor: Achieving Both Authenticity and Cross-Domain Capability in Image Editing Via Hypernetworks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In response, we propose an innovative image editing method called HyperEditor, which utilizes weight factors generated by hypernetworks to reassign the weights of the pre-trained StyleGAN2’s generator. |
Hai Zhang; Chunwei Wu; Guitao Cao; Hailing Wang; Wenming Cao; | aaai | 2024-02-20 |
| 485 | S2WAT: Image Style Transfer Via Hierarchical Vision Transformer Using Strips Window Attention Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper introduces Strips Window Attention Transformer (S2WAT), a novel hierarchical vision transformer designed for style transfer. |
Chiyu Zhang; Xiaogang Xu; Lei Wang; Zaiyan Dai; Jun Yang; | aaai | 2024-02-20 |
| 486 | FedST: Federated Style Transfer Learning for Non-IID Image Segmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a novel federated image segmentation method based on style transfer, FedST, by using a denoising diffusion probabilistic model to achieve feature disentanglement and image synthesis of cross-domain image data between multiple clients. |
BOYUAN MA et. al. | aaai | 2024-02-20 |
| 487 | Learning to Manipulate Artistic Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose an arbitrary Style Image Manipulation Network (SIM-Net), which leverages semantic-free information as guidance and a region transportation strategy in a self-supervised manner for image generation. |
Wei Guo; Yuqi Zhang; De Ma; Qian Zheng; | aaai | 2024-02-20 |
| 488 | FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present FPRF, a feed-forward photorealistic style transfer method for large-scale 3D neural radiance fields. |
GeonU Kim; Kim Youwang; Tae-Hyun Oh; | aaai | 2024-02-20 |
| 489 | Scalable Motion Style Transfer with Constrained Diffusion Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. |
Wenjie Yin; Yi Yu; Hang Yin; Danica Kragic; Mårten Björkman; | aaai | 2024-02-20 |
| 490 | ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Small model-based approaches can preserve the content strucuture, but fail to produce highly realistic stylized images and introduce artifacts and disharmonious patterns; Pre-trained large-scale model-based approaches can generate highly realistic stylized images but struggle with preserving the content structure. To address the above issues, we propose ArtBank, a novel artistic style transfer framework, to generate highly realistic stylized images while preserving the content structure of the content images. |
ZHANJIE ZHANG et. al. | aaai | 2024-02-20 |
| 491 | SEIT: Structural Enhancement for Unsupervised Image Translation in Frequency Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an unsupervised image translation method with structural enhancement in frequency domain named SEIT. |
ZHIFENG ZHU et. al. | aaai | 2024-02-20 |
| 492 | Improving 2D-3D Dense Correspondences with Diffusion Models for 6D Object Pose Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we compare image-to-image translation networks based on GANs and diffusion models for the downstream task of 6D object pose estimation. |
Peter Hönig; Stefan Thalhammer; Markus Vincze; | arxiv-cs.CV | 2024-02-09 |
| 493 | Application of Multi-level Adaptive Neural Network Based on Optimization Algorithm in Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Hong-an Li; Lanye Wang; Jun Liu; | Multim. Tools Appl. | 2024-02-09 |
| 494 | Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To address his issue, we propose a strategy for inducing a shape bias to CNN training. |
Peter Hönig; Stefan Thalhammer; Jean-Baptiste Weibel; Matthias Hirschmanner; Markus Vincze; | arxiv-cs.CV | 2024-02-07 |
| 495 | IGUANe: A 3D Generalizable CycleGAN for Multicenter Harmonization of Brain MR Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this study, we introduce IGUANe (Image Generation with Unified Adversarial Networks), an original 3D model that leverages the strengths of domain translation and straightforward application of style transfer methods for multicenter brain MR image harmonization. |
Vincent Roca; Grégory Kuchcinski; Jean-Pierre Pruvo; Dorian Manouvriez; Renaud Lopes; | arxiv-cs.CV | 2024-02-05 |
| 496 | ToonAging: Face Re-Aging Upon Artistic Portrait Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a novel one-stage method for face re-aging combined with portrait style transfer, executed in a single generative step. |
Bumsoo Kim; Abdul Muqeet; Kyuchul Lee; Sanghyun Seo; | arxiv-cs.CV | 2024-02-05 |
| 497 | ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce ConRF, a novel method of zero-shot stylization. |
XINGYU MIAO et. al. | arxiv-cs.CV | 2024-02-02 |
| 498 | Phrase Grounding-based Style Transfer for Single-Domain Generalized Object Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel phrase grounding-based style transfer (PGST) approach for the task. |
HAO LI et. al. | arxiv-cs.CV | 2024-02-02 |
| 499 | Towards Efficient Image and Video Style Transfer Via Distillation and Learnable Feature Transformation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
JING HUO et. al. | Comput. Vis. Image Underst. | 2024-02-01 |
| 500 | Panoptic-Level Image-to-Image Translation for Object Recognition and Visual Odometry Enhancement IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-to-image translation methods have progressed from only considering the image-level information to integrating the global- and instance-level information. However, only the … |
LIYUN ZHANG et. al. | IEEE Transactions on Circuits and Systems for Video … | 2024-02-01 |
| 501 | Transferring Human Emotions to Robot Motions Using Neural Policy Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The proposed approach was evaluated for both platforms, performing a total of 147 questionnaires asking human subjects to recognize the human motion style transferred to the robot motion for a predefined set of actions. |
Raul Fernandez-Fernandez; Bartek Łukawski; Juan G. Victores; Claudio Pacchierotti; | arxiv-cs.RO | 2024-02-01 |
| 502 | LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents LatentPatch, a new method for generating realistic images from a small dataset of only a few images. |
Benjamin Samuth; Julien Rabin; David Tschumperlé; Frédéric Jurie; | arxiv-cs.MM | 2024-01-30 |
| 503 | FreeStyle: Free Lunch for Text-guided Style Transfer Using Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce FreeStyle, an innovative style transfer method built upon a pre-trained large diffusion model, requiring no further optimization. |
FEIHONG HE et. al. | arxiv-cs.CV | 2024-01-28 |
| 504 | CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Specifically, we propose an innovative multi-task unified framework called CreativeSynth, based on the diffusion model with the ability to coordinate multimodal inputs. |
NISHA HUANG et. al. | arxiv-cs.CV | 2024-01-25 |
| 505 | CIMGEN: Controlled Image Manipulation By Finetuning Pretrained Generative Models on Limited Data Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Content creation and image editing can benefit from flexible user controls. A common intermediate representation for conditional image generation is a semantic map, that has … |
Chandrakanth Gudavalli; E. Rosten; L. Nataraj; S. Chandrasekaran; B. Manjunath; | ArXiv | 2024-01-23 |
| 506 | Image Translation As Diffusion Visual Programmers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the novel Diffusion Visual Programmer (DVP), a neuro-symbolic image translation framework. |
CHENG HAN et. al. | arxiv-cs.CV | 2024-01-18 |
| 507 | Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose Locally Adaptive Adversarial Color Attack (LAACA), empowering artists to protect their artwork from unauthorized style transfer by processing before public release. |
ZHONGLIANG GUO et. al. | arxiv-cs.CV | 2024-01-17 |
| 508 | Key-point Guided Deformable Image Manipulation Using Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a Key-point-guided Diffusion probabilistic Model (KDM) that gains precise control over images by manipulating the object’s key-point. |
SEOK-HWAN OH et. al. | arxiv-cs.CV | 2024-01-16 |
| 509 | HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In the specific, our model is constructed based on Latent Diffusion Model (LDM) and elaborately designed to absorb content and style instance as conditions of LDM. |
HANZHANG WANG et. al. | arxiv-cs.CV | 2024-01-11 |
| 510 | Let’s Go Shopping (LGS) – Web-Scale Image-Text Dataset for Visual Concept Understanding IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial … |
YATONG BAI et. al. | ArXiv | 2024-01-09 |
| 511 | Let’s Go Shopping (LGS) — Web-Scale Image-Text Dataset for Visual Concept Understanding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the Let’s Go Shopping (LGS) dataset, a large-scale public dataset with 15 million image-caption pairs from publicly available e-commerce websites. |
YATONG BAI et. al. | arxiv-cs.CV | 2024-01-09 |
| 512 | Domain Generalization for Face Forgery Detection By Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Although deep fake detection models have made significant progress, the challenge of performance degradation remains yet for unseen datasets. To address this, we introduce a novel … |
Taehoon Kim; Jongwook Choi; Hyunjin Cho; HyoungJun Lim; Jongwon Choi; | 2024 IEEE International Conference on Consumer Electronics … | 2024-01-06 |
| 513 | MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation By Prompts Redescription and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To make reconstruction explicit, we propose a prompt redescription strategy to realize a mirror effect between the source and reconstructed image in the diffusion model (MirrorDiffusion). |
Yupei Lin; Xiaoyu Xian; Yukai Shi; Liang Lin; | arxiv-cs.CV | 2024-01-06 |
| 514 | LipAT: Beyond Style Transfer for Controllable Neural Simulation of Lipstick Using Cosmetic Attributes Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Lipstick virtual try-on (VTO) experiences have become widespread across the e-commerce sector and assist users in eliminating the guesswork of shopping online. However, such … |
AMILA SILVA et. al. | 2024 IEEE/CVF Winter Conference on Applications of Computer … | 2024-01-03 |
| 515 | Unsupervised Exemplar-Based Image-to-Image Translation and Cascaded Vision Transformers for Tagged and Untagged Cardiac Cine MRI Registration Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Multi-modal registration between tagged and untagged cardiac cine magnetic resonance (MR) images remains difficult, due to the domain gap and large deformations between the two … |
Meng Ye; Mikael Kanski; Dong Yang; Leon Axel; Dimitris N. Metaxas; | 2024 IEEE/CVF Winter Conference on Applications of Computer … | 2024-01-03 |
| 516 | Neural Style Protection: Counteracting Unauthorized Neural Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Arbitrary neural style transfer is an advanced AI technique that can effectively synthesize pictures with an artistic style similar to a given source picture. However, if such an … |
Yaxin Li; Jie Ren; Han Xu; Hui Liu; | 2024 IEEE/CVF Winter Conference on Applications of Computer … | 2024-01-03 |
| 517 | PhotoStyle60: A Photographic Style Dataset for Photo Authorship Attribution and Photographic Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Photography, like painting, allows artists to express themselves through their unique style. In digital photography, this is achieved not only with the choice of the subject and … |
Marco Cotogni; Marco Arazzi; Claudio Cusano; | IEEE Transactions on Multimedia | 2024-01-01 |
| 518 | InverMulT-STP: Closed-Loop Transformer Seismic AVA Inversion With Synthetic Data Style Transfer Pretraining Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Prestack seismic data amplitude variation with angle (AVA) inversion is critical in identifying oil and gas reservoirs. Recently, deep learning (DL) has gained significant … |
Xudong Liu; Bangyu Wu; Chao Wei; Xinfei Yan; | IEEE Transactions on Geoscience and Remote Sensing | 2024-01-01 |
| 519 | OmniStyleGAN for Style-Guided Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Qianyi Zhao; Mengyin Wang; Qing Zhang; Fasheng Wang; Fuming Sun; | Chinese Conference on Pattern Recognition and Computer … | 2024-01-01 |
| 520 | Embedding Secret Message in Chinese Characters Via Glyph Perturbation and Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Glyph perturbation adjusts the characters’ structures and strokes to make the original characters change subtly, which cannot be detected by the naked eye. These generated … |
YE YAO et. al. | IEEE Transactions on Information Forensics and Security | 2024-01-01 |
| 521 | Multi-level Patch Transformer for Style Transfer with Single Reference Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Yue He; Lan Chen; Yu-Jie Yuan; Shu-Yu Chen; Lin Gao; | International Conference on Computational Visual Media | 2024-01-01 |
| 522 | Self-Supervised Learning Guided By SAR Image Factors for Terrain Classification Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Effective feature representation is the key to synthetic aperture radar (SAR) image terrain classification. Limited by the abstract appearance and the scarcity of high-quality … |
ZHONGLE REN et. al. | IEEE Transactions on Geoscience and Remote Sensing | 2024-01-01 |
| 523 | SemanticSplatStylization: Semantic Scene Stylization Based on 3D Gaussian Splatting and Class-based Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Saptarshi Neil Sinha; Holger Graf; Michael Weinmann; | Eurographics Workshop on Graphics and Cultural Heritage | 2024-01-01 |
| 524 | GCSANet: Arbitrary Style Transfer With Global Context Self-Attentional Network Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Arbitrary style transfer is attracting increasing attention in the computer vision community due to its application flexibility. Existing approaches directly fuse deep style … |
Zhongyu Bai; Hongli Xu; X. Zhang; Qichuan Ding; | IEEE Transactions on Multimedia | 2024-01-01 |
| 525 | Open-Set: ID Card Presentation Attack Detection Using Neural Style Transfer IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The accurate detection of ID card Presentation Attacks (PA) is becoming increasingly important due to the rising number of online/remote services that require the presentation of … |
Reuben P. Markham; Juan M. Espín López; Mario Nieto-Hidalgo; Juan E. Tapia; | IEEE Access | 2024-01-01 |
| 526 | SCSP: An Unsupervised Image-to-Image Translation Network Based on Semantic Cooperative Shape Perception Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This article introduces a novel approach to unsupervised image-to-image translation, aiming to overcome the limitations of existing methods in accurately capturing the shape of … |
Xi Yang; Zihan Wang; Ziyu Wei; Dong Yang; | IEEE Transactions on Multimedia | 2024-01-01 |
| 527 | Ultrasound Despeckling With GANs and Cross Modality Transfer Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Ultrasound images are corrupted by a type of signal-dependent noise, called speckle, difficult to remove or attenuate with the classical denoising methods. On the contrary, … |
DIOGO FRÓIS VIEIRA et. al. | IEEE Access | 2024-01-01 |
| 528 | Towards High-Quality Photorealistic Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Preserving important textures of the content image and achieving prominent style transfer results remains a challenge in the field of image style transfer. This challenge arises … |
HONGWEI DING et. al. | IEEE Transactions on Multimedia | 2024-01-01 |
| 529 | Reconstruction of Mammography Projections Using Image-to-Image Translation Techniques Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Joana Cristo Santos; M. S. Santos; P. Abreu; | ESANN 2024 proceesdings | 2024-01-01 |
| 530 | AdvST: Generating Unrestricted Adversarial Images Via Style Transfer IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent years have witnessed extensive applications of Deep Neural Networks (DNNs) in various vision tasks. However, DNNs are vulnerable to adversarial images crafted by … |
XIAOMENG WANG et. al. | IEEE Transactions on Multimedia | 2024-01-01 |
| 531 | Feature Consistency-Based Style Transfer for Landscape Images Using Dual-Channel Attention Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the rapid development of artificial intelligence technology, style transfer has become an important topic in current research. However, existing models are deficient in … |
Qiang Zhang; Shuai Wang; Dong Cui; | IEEE Access | 2024-01-01 |
| 532 | A Generative Adversarial Network AMS-CycleGAN for Multi-Style Image Transformation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The objective of image style transfer is to create an image that has the artistic features of a reference style image while also retaining the details of the original content … |
XIAODI RANG et. al. | IEEE Access | 2024-01-01 |
| 533 | Multiscale Spatial–Spectral Invertible Compensation Network for Hyperspectral Remote Sensing Image Denoising Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Hyperspectral image (HSI) has fine spectral resolution and abundant spatial information to detect subtle differences between targets. However, it is heavily contaminated with … |
Huiyang Li; Kai Ren; Weiwei Sun; Gang Yang; Xiangchao Meng; | IEEE Transactions on Geoscience and Remote Sensing | 2024-01-01 |
| 534 | Consistent Panoramic Video Style Transfer Via Temporal-Spatial Cross Perception Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Weiyu Wang; Chunmei Qing; Junpeng Tan; Xiangmin Xu; | International Conference on Intelligent Computing | 2024-01-01 |
| 535 | DR-AVIT: Toward Diverse and Realistic Aerial Visible-to-Infrared Image Translation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-to-image (I2I) translation methods based on generative adversarial networks (GANs) have shown general solutions for aerial visible-to-infrared image translation (AVIT) task. … |
Zonghao Han; Shun Zhang; Yuru Su; Xiaoning Chen; Shaohui Mei; | IEEE Transactions on Geoscience and Remote Sensing | 2024-01-01 |
| 536 | Multi-Source Style Transfer Via Style Disentanglement Network IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Despite the great success of deep neural networks for style transfer tasks, the entanglement of content and style in images leads to more style information not being captured. To … |
Quan Wang; Sheng Li; Zichi Wang; Xinpeng Zhang; Guorui Feng; | IEEE Transactions on Multimedia | 2024-01-01 |
| 537 | Color-to-gray Image Conversion Using Salient Colors and Radial Basis Functions Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Abstract. Color-to-gray image conversion is commonly used in applications such as printing, e-ink display, image stylization. Effective decolorization methods aim to maintain the … |
Lina Zhang; Yi Wan; | Journal of Electronic Imaging | 2024-01-01 |
| 538 | UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The rapid advancement of diffusion models (DMs) has not only transformed various real-world industries but has also introduced negative societal concerns, including the generation … |
YIHUA ZHANG et. al. | ArXiv | 2024-01-01 |
| 539 | Comparison of Deep Learning Image-to-image Models for Medical Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Zeyu Yang; Frank G. Zöllner; | Bildverarbeitung für die Medizin | 2024-01-01 |
| 540 | Self-Supervised Underwater Image Generation for Underwater Domain Pre-Training Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The rapid progress in computer vision has presented new opportunities for enhancing the visual capabilities of underwater robots. However, most deep learning-based visual … |
Zhi-zong Wu; Zhengxing Wu; Xingyu Chen; Yue Lu; Junzhi Yu; | IEEE Transactions on Instrumentation and Measurement | 2024-01-01 |
| 541 | Disrupting Anti-Spoofing Systems By Images of Consistent Identity Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Face anti-spoofing aims to distinguish between live and spoof images to ensure the authenticity and reliability of face recognition. Methods based on convolutional neural networks … |
Feng Ding; Zihan Jiang; Yue Zhou; Jianfeng Xu; Guopu Zhu; | IEEE Signal Processing Letters | 2024-01-01 |
| 542 | Authorship Style Transfer with Inverse Transfer Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
ZHONGHUI SHAO et. al. | AI Open | 2024-01-01 |
| 543 | CycleGAN for Flash-to-Ambient Image Conversion: A Style Transfer Approach Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the increasing prominence of mobile photography, capturing high-quality images in low-light conditions, especially with flash, remains a significant challenge. This study … |
SIDDHARTH RAMANATHAN et. al. | IEEE Access | 2024-01-01 |
| 544 | Progressive Fourier Adversarial Domain Adaptation for Object Classification and Retrieval Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Domain adaptation has been extensively explored as a means of transferring knowledge from the labeled source domain to the unlabeled target domain with disparate data … |
TIANBAO LI et. al. | IEEE Transactions on Multimedia | 2024-01-01 |
| 545 | Side-Scan Sonar Image Classification With Zero-Shot and Style Transfer IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Side-scan sonar (SSS) has become an important tool for ocean exploration due to its practicality and reliability. Existing approaches for SSS image classification mainly rely on … |
Zhongyu Bai; Hongli Xu; Qichuan Ding; Xiangyue Zhang; | IEEE Transactions on Instrumentation and Measurement | 2024-01-01 |
| 546 | US-GAN: Ultrasound Image-Specific Feature Decomposition for Fine Texture Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Ultrasound images acquired through various measuring devices may have different styles, and each style may be specialized for diagnosing specific diseases. Accordingly, ultrasound … |
S. Kim; B. Song; | IEEE Access | 2024-01-01 |
| 547 | Visible-to-Infrared Image Translation for Matching Tasks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Visible-to-infrared image translation is an important way to enrich infrared data. However, the reliability of the data generated by image translation in downstream tasks has … |
Decao Ma; Shaopeng Li; Juan Su; Yong Xian; Tao Zhang; | IEEE Journal of Selected Topics in Applied Earth … | 2024-01-01 |
| 548 | Fine-Grained Human Hair Segmentation Using A Text-to-Image Diffusion Model Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Human hair segmentation is essential for face recognition and for achieving natural transformation of style transfer. However, it remains a challenging task due to the diverse … |
Dohyun Kim; Euna Lee; Daehyun Yoo; Hongchul Lee; | IEEE Access | 2024-01-01 |
| 549 | RainSD: Rain Style Diversification Module for Image Synthesis Enhancement Using Feature-Level Style Distribution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, a synthetic road dataset with sensor blockage generated from real road dataset BDD100K is suggested in the format of BDD100K annotation. |
HYEONJAE JEON et. al. | arxiv-cs.CV | 2023-12-31 |
| 550 | RAST: Restorable Arbitrary Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: The objective of arbitrary style transfer is to apply a given artistic or photo-realistic style to a target image. Although current methods have shown some success in transferring … |
Yingnan Ma; Chenqiu Zhao; Bingran Huang; Xudong Li; Anup Basu; | ACM Transactions on Multimedia Computing, Communications … | 2023-12-30 |
| 551 | Comparison of Transfer Style Using A CycleGAN Model with Data Augmentation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: . Image-to-image translation (I2I) is a specialized technique aimed at converting images from one domain to another while retaining their intrinsic content. This process involves … |
Gerardo Lugo-Torres; J. E. Rodríguez; D. Peralta-Rodríguez; Hiram Calvo; | Computación y Sistemas (CyS) | 2023-12-27 |
| 552 | Physical Adversarial Attack in Artificial Intelligence of Things Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the continuous development of wireless communication and artificial intelligence technology, Internet of Things (IoT) technology has made great progress. Deep learning … |
Xin Ma; Kai Yang; Chuanzhen Zhang; Hualing Li; Xin Zheng; | IET Commun. | 2023-12-22 |
| 553 | Text Fact Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content. To cover more text modification applications, such as adapting past news for current events and repurposing educational materials, we propose the task of text fact transfer, which seeks to transfer the factual content of a source text between topics without modifying its style. |
Nishant Balepur; Jie Huang; Kevin Chang; | emnlp | 2023-12-22 |
| 554 | Open-Set: ID Card Presentation Attack Detection Using Neural Transfer Style Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work explores ID card Presentation Attack Instruments (PAI) in order to improve the generation of samples with four Generative Adversarial Networks (GANs) based image translation models and analyses the effectiveness of the generated data for training fraud detection systems. |
Reuben Markham; Juan M. Espin; Mario Nieto-Hidalgo; Juan E. Tapia; | arxiv-cs.CV | 2023-12-21 |
| 555 | DETER: Detecting Edited Regions for Deterring Generative Manipulations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To counteract the shortcomings, we introduce DETER, a large-scale dataset for DETEcting edited image Regions and deterring modern advanced generative manipulations. |
SAI WANG et. al. | arxiv-cs.CV | 2023-12-16 |
| 556 | LogoStyleFool: Vitiating Video Recognition Systems Via Logo Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we focus on the video black-box setting and propose a novel attack framework named LogoStyleFool by adding a stylized logo to the clean video. |
YUXIN CAO et. al. | arxiv-cs.CV | 2023-12-15 |
| 557 | Towards Better Morphed Face Images Without Ghosting Artifacts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a method for automatic prevention of ghosting artifacts based on a pixel-wise alignment during morph generation. |
Clemens Seibold; Anna Hilsmann; Peter Eisert; | arxiv-cs.CV | 2023-12-13 |
| 558 | Scalable Motion Style Transfer with Constrained Diffusion Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent image transfer works show the potential of independent training on each domain by leveraging implicit bridging between diffusion models, with the content preservation, however, limited to simple data patterns. We address this by imposing biased sampling in backward diffusion while maintaining the domain independence in the training stage. |
Wenjie Yin; Yi Yu; Hang Yin; Danica Kragic; Mårten Björkman; | arxiv-cs.CV | 2023-12-12 |
| 559 | Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose Diffusion Cocktail (Ditail), a training-free method that transfers style and content information between multiple diffusion models. |
Haoming Liu; Yuanhe Guo; Shengjie Wang; Hongyi Wen; | arxiv-cs.CV | 2023-12-11 |
| 560 | ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Small model-based approaches can preserve the content strucuture, but fail to produce highly realistic stylized images and introduce artifacts and disharmonious patterns; Pre-trained large-scale model-based approaches can generate highly realistic stylized images but struggle with preserving the content structure. To address the above issues, we propose ArtBank, a novel artistic style transfer framework, to generate highly realistic stylized images while preserving the content structure of the content images. |
ZHANJIE ZHANG et. al. | arxiv-cs.CV | 2023-12-11 |
| 561 | AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This work proposes a lightweight but effective model, AesFA — Aesthetic Feature-Aware NST. |
Joonwoo Kwon; Sooyoung Kim; Yuewei Lin; Shinjae Yoo; Jiook Cha; | arxiv-cs.CV | 2023-12-10 |
| 562 | Neutral Editing Framework for Diffusion-based Video Editing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text-conditioned image editing has succeeded in various types of editing based on a diffusion framework. Unfortunately, this success did not carry over to a video, which continues … |
Sunjae Yoon; Gwanhyeong Koo; Jiajing Hong; Changdong Yoo; | ArXiv | 2023-12-10 |
| 563 | Anything to Glyph: Artistic Font Synthesis Via Text-to-Image Diffusion Model IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The automatic generation of artistic fonts is a challenging task that attracts many research interests. Previous methods specifically focus on glyph or texture style transfer. … |
CHANGSHUO WANG et. al. | SIGGRAPH Asia 2023 Conference Papers | 2023-12-10 |
| 564 | BARET : Balanced Attention Based Real Image Editing Driven By Target-text Inversion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Image editing approaches with diffusion models have been rapidly developed, yet their applicability are subject to requirements such as specific editing types (e.g., foreground or background object editing, style transfer), multiple conditions (e.g., mask, sketch, caption), and time consuming fine-tuning of diffusion models. For alleviating these limitations and realizing efficient real image editing, we propose a novel editing technique that only requires an input image and target text for various editing types including non-rigid edits without fine-tuning diffusion model. |
YUMING QIAO et. al. | arxiv-cs.CV | 2023-12-09 |
| 565 | MuVieCAST: Multi-View Consistent Artistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce MuVieCAST, a modular multi-view consistent style transfer network architecture that enables consistent style transfer between multiple viewpoints of the same scene. |
Nail Ibrahimli; Julian F. P. Kooij; Liangliang Nan; | arxiv-cs.CV | 2023-12-08 |
| 566 | Towards 4D Human Video Stylization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present a first step towards 4D (3D and time) human video stylization, which addresses style transfer, novel view synthesis and human animation within a unified framework. |
Tiantian Wang; Xinxin Zuo; Fangzhou Mu; Jian Wang; Ming-Hsuan Yang; | arxiv-cs.CV | 2023-12-07 |
| 567 | Style Transfer to Calvin and Hobbes Comics Using Stable Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This project report summarizes our journey to perform stable diffusionfine-tuning on a dataset containing Calvin and Hobbes comics. |
Asvin Kumar Venkataramanan; Sloke Shrestha; Sundar Sripada Venugopalaswamy Sriraman; | arxiv-cs.CV | 2023-12-06 |
| 568 | LEGO: Learning EGOcentric Action Frame Generation Via Visual Instruction Tuning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce a novel problem — egocentric action frame generation. |
BOLIN LAI et. al. | arxiv-cs.CV | 2023-12-06 |
| 569 | Geometric Style Transfer for Face Portraits Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Geometric style transfer jointly stylizes the texture and geometry of a content image to better match a style image, which has attracted widespread attention due to its various … |
Miaomiao Dai; Hao Yin; Ran Yi; Lizhuang Ma; | Proceedings of the 5th ACM International Conference on … | 2023-12-06 |
| 570 | Multimodality-guided Image Style Transfer Using Cross-modal GAN Inversion IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Unfortunately, many TIST approaches produce undesirable artifacts in the transferred images. To address this issue, we present a novel method to achieve much improved style transfer based on text guidance. |
Hanyu Wang; Pengxiang Wu; Kevin Dela Rosa; Chen Wang; Abhinav Shrivastava; | arxiv-cs.CV | 2023-12-04 |
| 571 | MMFusion: Combining Image Forensic Filters for Visual Manipulation Detection and Localization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Recent image manipulation localization and detection techniques typically leverage forensic artifacts and traces that are produced by a noise-sensitive filter, such as SRM or Bayar convolution. In this paper, we showcase that different filters commonly used in such approaches excel at unveiling different types of manipulations and provide complementary forensic traces. |
Kostas Triaridis; Konstantinos Tsigos; Vasileios Mezaris; | arxiv-cs.CV | 2023-12-04 |
| 572 | SASSL: Enhancing Self-Supervised Learning Via Neural Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This results in distorted augmented samples with compromised semantic information, ultimately impacting downstream performance. To overcome this limitation, we propose SASSL: Style Augmentations for Self Supervised Learning, a novel data augmentation technique based on Neural Style Transfer. |
RENAN A. ROJAS-GOMEZ et. al. | arxiv-cs.CV | 2023-12-02 |
| 573 | Beyond Entropy: Style Transfer Guided Single Image Continual Test-Time Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In detail, when using a single image, the instability caused by batch normalization layers and entropy loss significantly destabilizes many existing methods in real-world cTTA scenarios. To overcome these challenges, we present BESTTA, a novel single image continual test-time adaptation method guided by style transfer, which enables stable and efficient adaptation to the target environment by transferring the style of the input image to the source style. |
Younggeol Cho; Youngrae Kim; Dongman Lee; | arxiv-cs.CV | 2023-11-30 |
| 574 | Vector Gradient Stroke Stylized Neural Network Painting Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This study focuses on the oil painting brush style transfer in deep convolutional network-based style painting models. We proposes an SVG gradient vectorization process to … |
Jia-Shuan Lin; Tung-Ju Hsieh; | SIGGRAPH Asia 2023 Posters | 2023-11-28 |
| 575 | SubmergeStyleGAN: Synthetic Underwater Data Generation with Style Transfer for Domain Adaptation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Underwater computer vision applications are challenged by limited access to annotated underwater datasets. Additionally, convolutional neural networks (CNNs) trained on in-air … |
Mohamed E. Fathy; S. A. Mohamed; Mohammed I. Awad; Hossam E. Abd El Munim; | 2023 International Conference on Digital Image Computing: … | 2023-11-28 |
| 576 | Fine-grained Appearance Transfer with Diffusion Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: Image-to-image translation (I2I), and particularly its subfield of appearance transfer, which seeks to alter the visual appearance between images while maintaining structural … |
YUTENG YE et. al. | ArXiv | 2023-11-27 |
| 577 | InstaStyle: Inversion Noise of A Stylized Image Is Secretly A Style Adviser IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose InstaStyle, a novel approach that excels in generating high-fidelity stylized images with only a single reference image. |
XING CUI et. al. | arxiv-cs.CV | 2023-11-25 |
| 578 | Z*: Zero-shot Style Transfer Via Attention Rearrangement IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Despite the remarkable progress in image style transfer, formulating style in the context of art is inherently subjective and challenging. In contrast to existing learning/tuning … |
Yingying Deng; Xiangyu He; Fan Tang; Weiming Dong; | ArXiv | 2023-11-25 |
| 579 | Neural Style Transfer for Computer Games Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we present an approach for injecting depth-aware NST as part of the 3D rendering pipeline. |
Eleftherios Ioannou; Steve Maddock; | arxiv-cs.CV | 2023-11-24 |
| 580 | Highly Detailed and Temporal Consistent Video Stylization Via Synchronized Multi-Frame Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a synchronized multi-frame diffusion framework to maintain both the visual details and the temporal consistency. |
Minshan Xie; Hanyuan Liu; Chengze Li; Tien-Tsin Wong; | arxiv-cs.CV | 2023-11-24 |
| 581 | FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike existing methods that require either training auxiliary networks or fine-tuning a large pre-trained backbone, or both, to harmonize a foreground object with a painterly-style background image, our FreePIH tames the denoising process as a plug-in module for foreground image style transfer. Specifically, we find that the very last few steps of the denoising (i.e., generation) process strongly correspond to the stylistic information of images, and based on this, we propose to augment the latent features of both the foreground and background images with Gaussians for a direct denoising-based harmonization. |
Ruibin Li; Jingcai Guo; Song Guo; Qihua Zhou; Jie Zhang; | arxiv-cs.CV | 2023-11-24 |
| 582 | A New Benchmark and Model for Challenging Image Manipulation Detection IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To investigate the State-of-The-Art (SoTA) IMD methods in those challenging conditions, we introduce a new Challenging Image Manipulation Detection (CIMD) benchmark dataset, which consists of two subsets, for evaluating editing-based and compression-based IMD methods, respectively. |
Zhenfei Zhang; Mingyang Li; Ming-Ching Chang; | arxiv-cs.CV | 2023-11-23 |
| 583 | Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, most current methods require reference to stylized images and cannot individually stylize specific objects. To overcome this limitation, we propose the Soulstyler framework, which allows users to guide the stylization of specific objects in an image through simple textual descriptions. |
JUNHAO CHEN et. al. | arxiv-cs.CV | 2023-11-22 |
| 584 | 3D Face Style Transfer with A Hybrid Solution of NeRF and Mesh Rasterization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we tackle the problem of 3D face style transfer which aims at generating stylized novel views of a 3D human face with multi-view consistency. |
Jianwei Feng; Prateek Singhal; | arxiv-cs.CV | 2023-11-22 |
| 585 | Hairstyle-and-identity-aware Facial Image Style Transfer with Region-guiding Masks Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Hsin-Ying Wang; Chiu-Wei Chien; Ming-Han Tsai; I-Chen Lin; | Multim. Tools Appl. | 2023-11-15 |
| 586 | FastBlend: A Powerful Model-Free Toolkit Making Video Stylization Easier Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: With the emergence of diffusion models and rapid development in image processing, it has become effortless to generate fancy images in tasks such as style transfer and image … |
ZHONGJIE DUAN et. al. | ArXiv | 2023-11-15 |
| 587 | PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. |
HUASHAN SUN et. al. | arxiv-cs.CL | 2023-11-14 |
| 588 | STEER: Unified Style Transfer with Expert Reinforcement IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we focus on arbitrary style transfer: rewriting a text from an arbitrary, unknown style to a target style. |
SKYLER HALLINAN et. al. | arxiv-cs.CL | 2023-11-13 |
| 589 | ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priors IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a new task for “stylizing” text-to-image models, namely text-driven stylized image generation, that further enhances editability in content creation. |
Jingwen Chen; Yingwei Pan; Ting Yao; Tao Mei; | arxiv-cs.CV | 2023-11-09 |
| 590 | SCONE-GAN: Semantic Contrastive Learning-based Generative Adversarial Network for An End-to-end Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: That is because these methods learn more frequent associations rather than the scene structures. To mitigate the problem, we propose SCONE-GAN that utilises graph convolutional networks to learn the objects dependencies, maintain the image structure and preserve its semantics while transferring images into the target domain. |
IMAN ABBASNEJAD et. al. | arxiv-cs.CV | 2023-11-07 |
| 591 | Optimal Image Transport on Sparse Dictionaries Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we derive a novel optimal image transport algorithm over sparse dictionaries by taking advantage of Sparse Representation (SR) and Optimal Transport (OT). |
Junqing Huang; Haihui Wang; Andreas Weiermann; Michael Ruzhansky; | arxiv-cs.CV | 2023-11-03 |
| 592 | Expanding Expressiveness of Diffusion Models with Limited Data Via Self-Distillation Based Fine-Tuning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain translation and text-guided image manipulation. In this paper, we propose Self-Distillation for Fine-Tuning diffusion models (SDFT), a methodology to address these challenges by leveraging diverse features from diffusion models pretrained on large source datasets. |
Jiwan Hur; Jaehyun Choi; Gyojin Han; Dong-Jae Lee; Junmo Kim; | arxiv-cs.CV | 2023-11-02 |
| 593 | Novel View Synthesis from A Single RGBD Image for Indoor Scenes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an approach for synthesizing novel view images from a single RGBD (Red Green Blue-Depth) input. |
Congrui Hetang; Yuping Wang; | arxiv-cs.CV | 2023-11-02 |
| 594 | CFA-GAN: Cross Fusion Attention and Frequency Loss for Image Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
XIANGTIAN ZHENG et. al. | Displays | 2023-11-01 |
| 595 | Histopathological Image Analysis with Style-Augmented Feature Domain Mixing for Improved Generalization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this study, we propose a feature domain style mixing technique that uses adaptive instance normalization to generate style-augmented versions of images. |
Vaibhav Khamankar; Sutanu Bera; Saumik Bhattacharya; Debashis Sen; Prabir Kumar Biswas; | arxiv-cs.CV | 2023-10-31 |
| 596 | An Implementation of Multimodal Fusion System for Intelligent Digital Human Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, an implementation scheme of an intelligent digital human generation system with multimodal fusion is proposed. |
Yingjie Zhou; Yaodong Chen; Kaiyue Bi; Lian Xiong; Hui Liu; | arxiv-cs.MM | 2023-10-31 |
| 597 | TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Consequently, the stylization results either fail to capture abundant and diversified local style patterns, or contain undesired semantic information of the style image and deviate from the global style distribution. To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects. |
Haibo Chen; Lei Zhao; Jun Li; Jian Yang; | mm | 2023-10-30 |
| 598 | Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To solve the problem, we propose Compositional Neural Painter, a novel stroke-based rendering framework which dynamically predicts the next painting region based on the current canvas, instead of dividing the image plane uniformly into painting regions. |
TENG HU et. al. | mm | 2023-10-30 |
| 599 | Improving The Transferability of Adversarial Examples with Arbitrary Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Hence, we propose a novel attack method named Style Transfer Method (STM) that utilizes a proposed arbitrary style transfer network to transform the images into different domains. |
ZHIJIN GE et. al. | mm | 2023-10-30 |
| 600 | Generative AI Model for Artistic Style Transfer Using Convolutional Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a comprehensive overview of a novel technique for style transfer using Convolutional Neural Networks (CNNs). |
Jonayet Miah; Duc M Cao; Md Abu Sayed; Md. Sabbirul Haque; | arxiv-cs.CV | 2023-10-27 |
| 601 | Rethinking Neural Style Transfer: Generating Personalized and Watermarked Stylized Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Neural style transfer (NST) has attracted many research interests recent years. The existing NST schemes could only generate one stylized image from a content-style image pair. … |
Quan Wang; Sheng Li; Xinpeng Zhang; Guorui Feng; | Proceedings of the 31st ACM International Conference on … | 2023-10-26 |
| 602 | Style Transfer Meets Super-Resolution: Advancing Unpaired Infrared-to-Visible Image Translation with Detail Enhancement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The problem of unpaired infrared-to-visible image translation has gained significant attention due to its ability to generate visible images with color information from low-detail … |
Yirui Shen; Jingxuan Kang; Shuang Li; Zhenjie Yu; Shuigen Wang; | Proceedings of the 31st ACM International Conference on … | 2023-10-26 |
| 603 | Interactive Image Style Transfer Guided By Graffiti Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Neural style transfer (NST) can quickly produce impressive artistic images, which allows ordinary people to become painter. The brushstrokes of stylized images created by the … |
Quan Wang; Yanli Ren; Xinpeng Zhang; Guorui Feng; | Proceedings of the 31st ACM International Conference on … | 2023-10-26 |
| 604 | Region-controlled Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they fail to control the strength of textures in different regions of the content image. To address this issue, we propose a training method that uses a loss function to constrain the style intensity in different regions. |
Junjie Kang; Jinsong Wu; Shiqi Jiang; | arxiv-cs.CV | 2023-10-24 |
| 605 | Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a Non-isotropic Gaussian Diffusion Model (NGDM) for image-to-image translation and image editing, which require translating or editing the source image while preserving the image regions irrelevant to the translation/editing task. |
Xi Yu; Xiang Gu; Haozhi Liu; Jian Sun; | nips | 2023-10-24 |
| 606 | ViSt3D: Video Stylization with 3D CNN Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To the best of our knowledge, we present the first approach to video stylization using 3D CNN directly, building upon insights from 2D image stylization. |
Ayush Pande; Gaurav Sharma; | nips | 2023-10-24 |
| 607 | ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. |
YA SHENG SUN et. al. | nips | 2023-10-24 |
| 608 | HQ-I2IT: Redesign The Optimization Scheme to Improve Image Quality in CycleGAN-based Image Translation Systems Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The image‐to‐image translation (I2IT) task aims to transform images from the source domain into the specified target domain. State‐of‐the‐art CycleGAN‐based translation algorithms … |
YIPENG ZHANG et. al. | IET Image Process. | 2023-10-24 |
| 609 | RePoseDM: Recurrent Pose Alignment and Gradient Guidance for Pose Guided Image Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Due to the leakage of the source pose in conditional guidance, we propose gradient guidance from pose interaction fields, which output the distance from the valid pose manifold given a predicted pose as input. |
Anant Khandelwal; | arxiv-cs.CV | 2023-10-24 |
| 610 | Text Fact Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Text style transfer is a prominent task that aims to control the style of text without inherently changing its factual content. To cover more text modification applications, such as adapting past news for current events and repurposing educational materials, we propose the task of text fact transfer, which seeks to transfer the factual content of a source text between topics without modifying its style. |
Nishant Balepur; Jie Huang; Kevin Chen-Chuan Chang; | arxiv-cs.CL | 2023-10-22 |
| 611 | Ladder Bottom-up Convolutional Bidirectional Variational Autoencoder for Image Translation of Dotted Arabic Expiration Dates Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes an approach of Ladder Bottom-up Convolutional Bidirectional Variational Autoencoder (LCBVAE) architecture for the encoder and decoder, which is trained on the image translation of the dotted Arabic expiration dates by reconstructing the Arabic dotted expiration dates into filled-in expiration dates. |
Ahmed Zidane; Ghada Soliman; | arxiv-cs.CV | 2023-10-21 |
| 612 | CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper introduces Cyclenet, a novel but simple method that incorporates cycle consistency into DMs to regularize image manipulation. |
Sihan Xu; Ziqiao Ma; Yidong Huang; Honglak Lee; Joyce Chai; | arxiv-cs.CV | 2023-10-19 |
| 613 | TOSS:High-quality Text-guided Novel View Synthesis from A Single Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image. |
YUKAI SHI et. al. | arxiv-cs.CV | 2023-10-16 |
| 614 | TOSS: High-quality Text-guided Novel View Synthesis from A Single Image IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we present TOSS, which introduces text to the task of novel view synthesis (NVS) from just a single RGB image. While Zero-1-to-3 has demonstrated impressive … |
YUKAI SHI et. al. | ArXiv | 2023-10-16 |
| 615 | Chinese Painting Style Transfer Using Deep Generative Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we will study and leverage different state-of-the-art deep generative models for Chinese painting style transfer and evaluate the performance both qualitatively and quantitatively. |
Weijian Ma; Yanyang Kong; | arxiv-cs.CV | 2023-10-15 |
| 616 | LOVECon: Text-driven Training-Free Long Video Editing with ControlNet IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper aims to bridge the gap, establishing a simple and effective baseline for training-free diffusion model-based long video editing. |
Zhenyi Liao; Zhijie Deng; | arxiv-cs.CV | 2023-10-14 |
| 617 | Does Resistance to Style-transfer Equal Global Shape Bias? Measuring Network Sensitivity to Global Shape Configuration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The current benchmark for evaluating a model’s global shape bias is a set of style-transferred images with the assumption that resistance to the attack of style transfer is related to the development of global structure sensitivity in the model. In this work, we show that networks trained with style-transfer images indeed learn to ignore style, but its shape bias arises primarily from local detail. |
Ziqi Wen; Tianqin Li; Zhi Jing; Tai Sing Lee; | arxiv-cs.CV | 2023-10-11 |
| 618 | Large Capacity Generative Image Steganography Via Image Style Transfer and Feature-wise Deep Fusion IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Youqiang Sun; Jianyi Liu; Ru Zhang; | Applied Intelligence | 2023-10-11 |
| 619 | Cancellable Biometric Authentication System By Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, we have more and more opportunities to identify ourselves through information devices. In this paper, we propose a cancellable biometric authentication system, where … |
Souta Yamamoto; Hiroyuki Inaba; | 2023 IEEE 12th Global Conference on Consumer Electronics … | 2023-10-10 |
| 620 | Text-Guided Facial Image Manipulation for Wild Images Via Manipulation Direction-Based Loss Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This paper proposes a novel text-guided facial image manipulation approach to improve robustness against the diversity of input images. Conventional text-guided facial image … |
Yuto Watanabe; Ren Togo; Keisuke Maeda; Takahiro Ogawa; M. Haseyama; | 2023 IEEE International Conference on Image Processing … | 2023-10-08 |
| 621 | PFC-UNIT: Unsupervised Image-to-Image Translation with Pre-Trained Fine-Grained Classification Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Unsupervised image-to-image translation has gained great attention in data augmentation by allowing the translation of images from one domain to another while preserving their … |
Yu-Ying Liang; Yuan-Gen Wang; | 2023 IEEE International Conference on Image Processing … | 2023-10-08 |
| 622 | WAIT: Feature Warping for Animation to Illustration Video Translation Using GANs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we explore a new domain for video-to-video translation. |
SAMET HICSONMEZ et. al. | arxiv-cs.CV | 2023-10-07 |
| 623 | VTON-IT: Virtual Try-On Using Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we try to produce photo-realistic translated images through semantic segmentation and a generative adversarial architecture-based image translation network. |
Santosh Adhikari; Bishnu Bhusal; Prashant Ghimire; Anil Shrestha; | arxiv-cs.CV | 2023-10-06 |
| 624 | CineTransfer: Controlling A Robot to Imitate Cinematographic Style from A Single Example Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work presents CineTransfer, an algorithmic framework that drives a robot to record a video sequence that mimics the cinematographic style of an input video. |
Pablo Pueyo; Eduardo Montijano; Ana C. Murillo; Mac Schwager; | arxiv-cs.RO | 2023-10-05 |
| 625 | FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: For example, a malicious user can employ fine-tuning techniques to replicate the style of an artist without consent. In light of this concern, we propose FT-Shield, a watermarking solution tailored for the fine-tuning of text-to-image diffusion models. |
YINGQIAN CUI et. al. | arxiv-cs.CV | 2023-10-03 |
| 626 | PanoStyle: Semantic, Geometry-Aware and Shading Independent Photorealistic Style Transfer for Indoor Panoramic Scenes Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: While current style transfer models have achieved impressive results for the application of artistic style to generic images, they face challenges in achieving photorealistic … |
MUHAMMAD TUKUR et. al. | 2023 IEEE/CVF International Conference on Computer Vision … | 2023-10-02 |
| 627 | Color and Texture Dual Pipeline Lightweight Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To solve the problem, we propose a Color and Texture Dual Pipeline Lightweight Style Transfer CTDP method, which employs a dual pipeline method to simultaneously output the results of color and texture transfer. |
ShiQi Jiang; | arxiv-cs.CV | 2023-10-02 |
| 628 | Large-scale Apple Orchard Mapping from Multi-source Data Using The Semantic Segmentation Model with Image- To- Image Translation and Transfer Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
TINGTING ZHANG et. al. | Comput. Electron. Agric. | 2023-10-01 |
| 629 | Neural Style Transfer for 3D Meshes Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Style transfer is a popular research topic in the field of computer vision. In 3D stylization, a mesh model is deformed to achieve a specific geometric style. We explore a general … |
Hongyuan Kang; Xiaopan Dong; Juan Cao; Zhonggui Chen; | Graph. Model. | 2023-10-01 |
| 630 | Sketch Assisted Face Image Coding for Human and Machine Vision: A Joint Training Approach IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image coding is one of the most fundamental techniques and is widely used in image/video processing and multimedia communications. Current image coding methods are mainly … |
Xin Fang; Yiping Duan; Qiyuan Du; Xiaoming Tao; Fan Li; | IEEE Transactions on Circuits and Systems for Video … | 2023-10-01 |
| 631 | An Easy Zero-shot Learning Combination: Texture Sensitive Semantic Segmentation IceHrNet and Advanced Style Transfer Learning Strategy Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We proposed an easy method of Zero-Shot semantic segmentation by using style transfer. |
ZHIYONG YANG et. al. | arxiv-cs.CV | 2023-09-30 |
| 632 | Controlling Neural Style Transfer with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose the first deep Reinforcement Learning (RL) based architecture that splits one-step style transfer into a step-wise process for the NST task. |
CHENGMING FENG et. al. | arxiv-cs.CV | 2023-09-30 |
| 633 | Locally Stylized Neural Radiance Fields IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a stylization framework for NeRF based on local style transfer. |
Hong-Wing Pang; Binh-Son Hua; Sai-Kit Yeung; | iccv | 2023-09-27 |
| 634 | Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer By Permuting Textures Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose Pose Transfer by Permuting Textures, a self-driven human pose transfer approach that disentangles pose from texture at the patch-level. |
Nannan Li; Kevin J Shih; Bryan A. Plummer; | iccv | 2023-09-27 |
| 635 | Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Considering the difficulties in transferring highly structural patterns on the garments and discontinuous poses, existing methods often generate unsatisfactory results such as distorted textures and flickering artifacts. To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer. |
WING-YIN YU et. al. | iccv | 2023-09-27 |
| 636 | Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In order to achieve satisfying image and video style transfers, two different models are inevitably required with separate training processes on image and video domains, respectively. In this paper, we show that this can be precluded by introducing UniST, a Unified Style Transfer framework for both images and videos. |
Bohai Gu; Heng Fan; Libo Zhang; | iccv | 2023-09-27 |
| 637 | Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Existing methods require computationally expensive fine-tuning of diffusion models or additional neural network. To address this, here we propose a zero-shot contrastive loss for diffusion models that doesn’t require additional fine-tuning or auxiliary networks. |
Serin Yang; Hyunmin Hwang; Jong Chul Ye; | iccv | 2023-09-27 |
| 638 | Synthetic Latent Fingerprint Generation Using Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a simple and effective approach using style transfer and image blending to synthesize realistic latent fingerprints. |
Amol S. Joshi; Ali Dabouei; Nasser Nasrabadi; Jeremy Dawson; | arxiv-cs.CV | 2023-09-27 |
| 639 | StyleDiffusion: Controllable Disentangled Style Transfer Via Diffusion Models IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a new C-S disentangled framework for style transfer without using previous assumptions. |
Zhizhong Wang; Lei Zhao; Wei Xing; | iccv | 2023-09-27 |
| 640 | Scenimefy: Learning to Craft Anime Scene Via Semi-Supervised Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Despite promising attempts, previous efforts are still incompetent in achieving satisfactory results with consistent semantic preservation, evident stylization, and fine details. In this study, we propose Scenimefy, a novel semi-supervised image-to-image translation framework that addresses these challenges. |
Yuxin Jiang; Liming Jiang; Shuai Yang; Chen Change Loy; | iccv | 2023-09-27 |
| 641 | Cross-modal Latent Space Alignment for Image to Avatar Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel method for automatic vectorized avatar generation from a single portrait image. |
MANUEL LADRON DE GUEVARA et. al. | iccv | 2023-09-27 |
| 642 | WaveIPT: Joint Attention and Flow Alignment in The Wavelet Domain for Pose Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To leverage the advantages of both attention and flow simultaneously, we propose Wavelet-aware Image-based Pose Transfer (WaveIPT) to fuse the attention and flow in the wavelet domain. |
Liyuan Ma; Tingwei Gao; Haitian Jiang; Haibin Shen; Kejie Huang; | iccv | 2023-09-27 |
| 643 | Deep Style Transfer for Generation of Photo-realistic Synthetic Images of CNT Forests Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Carbon nanotubes (CNTs) are promising nano-materials with diverse applications in various fields, ranging from electronics and energy storage to biomedical applications. … |
Prashanth Kotha; Minasadat Attari; Matthew R. Maschmann; F. Bunyak; | 2023 IEEE Applied Imagery Pattern Recognition Workshop … | 2023-09-27 |
| 644 | UMFuse: Unified Multi View Fusion for Human Editing Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we explore the utilization of multiple views to minimize the issue of missing information and generate an accurate representation of the underlying human model. |
RISHABH JAIN et. al. | iccv | 2023-09-27 |
| 645 | AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce a novel metric, namely pattern repeatability, that quantifies the repetition of patterns in the style image. |
KIBEOM HONG et. al. | iccv | 2023-09-27 |
| 646 | In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To this end, we propose an approach, In-Style, that learns the style of the text queries and transfers it to uncurated web videos. |
Nina Shvetsova; Anna Kukleva; Bernt Schiele; Hilde Kuehne; | iccv | 2023-09-27 |
| 647 | Incorporating Ensemble and Transfer Learning For An End-To-End Auto-Colorized Image Detection Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents a novel approach that combines the advantages of transfer and ensemble learning approaches to help reduce training time and resource requirements while proposing a model to classify natural color and computer-colorized images. |
Ahmed Samir Ragab; Shereen Aly Taie; Howida Youssry Abdelnaby; | arxiv-cs.CV | 2023-09-25 |
| 648 | MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIP Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: On the other hand, diffusion style transfer methods also suffer from the same issue because the regional stylization control over the stylized output is ineffective. To address this problem, We propose a new method Multi-Object Segmented Arbitrary Stylization Using CLIP (MOSAIC), that can apply styles to different objects in the image based on the context extracted from the input prompt. |
PRAJWAL GANUGULA et. al. | arxiv-cs.CV | 2023-09-24 |
| 649 | MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we reveal that the common training method of stylization with NeRF, which generates stylized multi-view supervision by 2D style transfer models, causes the same object in supervision to show various states (color tone, details, etc.) in different views, leading NeRF to tend to smooth the texture details, further resulting in low-quality rendering for 3D multi-style transfer. |
Zijiang Yang; Zhongwei Qiu; Chang Xu; Dongmei Fu; | arxiv-cs.CV | 2023-09-24 |
| 650 | Portrait Stylization: Artistic Style Transfer with Auxiliary Networks for Human Face Stylization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper proposes the use of embeddings from an auxiliary pre-trained face recognition model to encourage the algorithm to propagate human face features from the content image to the final stylized result. |
Thiago Ambiel; | arxiv-cs.CV | 2023-09-23 |
| 651 | TextCLIP: Text-Guided Face Image Generation And Manipulation Without Adversarial Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose TextCLIP, a unified framework for text-guided image generation and manipulation without adversarial training. |
Xiaozhou You; Jian Zhang; | arxiv-cs.CV | 2023-09-21 |
| 652 | Boosting SAR Aircraft Detection Performance with Multi-Stage Domain Adaptation Training Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep learning has achieved significant success in various synthetic aperture radar (SAR) imagery interpretation tasks. However, automatic aircraft detection is still challenging … |
Wenbo Yu; Jiamu Li; Zijian Wang; Zhongjun Yu; | Remote. Sens. | 2023-09-20 |
| 653 | Retinex-guided Channel-grouping Based Patch Swap for Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Since the finite features harvested from one single aesthetic style image are inadequate to represent the rich textures of the content natural image, existing techniques treat the full-channel style feature patches as simple signal tensors and create new style feature patches via signal-level fusion, which ignore the implicit diversities existed in style features and thus fail for generating better stylised results. In this paper, we propose a Retinex theory guided, channel-grouping based patch swap technique to solve the above challenges. |
Chang Liu; Yi Niu; Mingming Ma; Fu Li; Guangming Shi; | arxiv-cs.CV | 2023-09-19 |
| 654 | Instant Photorealistic Style Transfer: A Lightweight and Adaptive Approach Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we propose an Instant Photorealistic Style Transfer (IPST) approach, designed to achieve instant photorealistic style transfer on super-resolution inputs without … |
Rong Liu; Enyu Zhao; Zhiyuan Liu; A. Feng; Scott John Easley; | ArXiv | 2023-09-18 |
| 655 | Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods often encounter challenges such as color tone distortions, dependency on pair-wise pre-training, inefficiency with high-resolution inputs, and the need for additional constraints in video style transfer tasks. To address these issues, we propose a Universal Photorealistic Style Transfer (UPST) framework that delivers accurate photorealistic style transfer on high-resolution images and videos without relying on pre-training. |
Rong Liu; Enyu Zhao; Zhiyuan Liu; Andrew Feng; Scott John Easley; | arxiv-cs.CV | 2023-09-18 |
| 656 | Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The acoustic language model we introduce for style transfer leverages self-supervised in-context learning, acquiring style transfer ability without relying on any speaker-parallel data, thereby overcoming data scarcity. |
YONGQI WANG et. al. | arxiv-cs.SD | 2023-09-14 |
| 657 | Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a novel nucleus-aware self-supervised pretraining framework for histopathology images. |
ZHIYUN SONG et. al. | arxiv-cs.CV | 2023-09-13 |
| 658 | Enhanced Residue Prediction for Lossless Coding of Multimodal Image Pairs Based on Image-to-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Multimodal medical imaging combine data obtained from multiple techniques simultaneously, yielding more detailed information about the content, which is a clear advantage over … |
Daniel S. Nicolau; Joao O. Parracho; Lucas A. Thomaz; Luís M. N. Tavora; Sérgio M. M. Faria; | 2023 11th European Workshop on Visual Information … | 2023-09-11 |
| 659 | PAI-Diffusion: Constructing and Serving A Family of Open Chinese Diffusion Models for Text-to-image Synthesis on The Cloud IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While existing diffusion models have shown promise in generating images from textual descriptions, they often neglect domain-specific contexts and lack robustness in handling the Chinese language. This paper introduces PAI-Diffusion, a comprehensive framework that addresses these limitations. |
CHENGYU WANG et. al. | arxiv-cs.CL | 2023-09-11 |
| 660 | MoEController: Instruction-based Arbitrary Image Manipulation with Mixture-of-Expert Controllers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a method with a mixture-of-expert (MOE) controllers to align the text-guided capacity of diffusion models with different kinds of human instructions, enabling our model to handle various open-domain image manipulation tasks with natural language instructions. |
Sijia Li; Chen Chen; Haonan Lu; | arxiv-cs.CV | 2023-09-08 |
| 661 | StyleAdapter: A Unified Stylized Image Generation Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose StyleAdapter, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning. |
ZHOUXIA WANG et. al. | arxiv-cs.CV | 2023-09-04 |
| 662 | Impact of Image Context for Single Deep Learning Face Morphing Attack Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This study investigates the impact of the alignment settings of input images on deep learning face morphing detection performance. |
Joana Pimenta; Iurii Medvedev; Nuno Gonçalves; | arxiv-cs.CV | 2023-09-01 |
| 663 | Shape-Consistent One-Shot Unsupervised Domain Adaptation for Rail Surface Defect Segmentation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep neural networks have greatly improved the performance of rail surface defect segmentation when the test samples have the same distribution as the training samples. However, … |
SHUAI MA et. al. | IEEE Transactions on Industrial Informatics | 2023-09-01 |
| 664 | Semantic Image Synthesis Via Class-Adaptive Cross-Attention Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In response, we designed a novel architecture where cross-attention layers are used in place of SPADE for learning shape-style correlations and so conditioning the image generation process. |
Tomaso Fontanini; Claudio Ferrari; Giuseppe Lisanti; Massimo Bertozzi; Andrea Prati; | arxiv-cs.CV | 2023-08-30 |
| 665 | MagicEdit: High-Fidelity and Temporally Coherent Video Editing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task. |
Jun Hao Liew; Hanshu Yan; Jianfeng Zhang; Zhongcong Xu; Jiashi Feng; | arxiv-cs.CV | 2023-08-28 |
| 666 | WSAM: Visual Explanations from Style Augmentation As Adversarial Attacker and Their Influence in Image Classification Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: With our augmentation strategy, all models not only present incredible robustness against image stylizing but also outperform all previous methods and surpass the state-of-the-art performance for the STL-10 dataset. |
Felipe Moreno-Vera; Edgar Medina; Jorge Poco; | arxiv-cs.CV | 2023-08-28 |
| 667 | ARF-Plus: Controlling Perceptual Factors in Artistic Radiance Fields for 3D Scene Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present ARF-Plus, a 3D neural style transfer framework offering manageable control over perceptual factors, to systematically explore the perceptual controllability in 3D scene stylization. |
Wenzhao Li; Tianhao Wu; Fangcheng Zhong; Cengiz Oztireli; | arxiv-cs.CV | 2023-08-23 |
| 668 | TeSTNeRF: Text-Driven 3D Style Transfer Via Cross-Modal Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Simply combining image/video style transfer methods and novel view synthesis methods results in flickering when changing viewpoints, while existing 3D style transfer methods learn styles from images instead of texts. To address this problem, we for the first time design an efficient text-driven model for 3D style transfer, named TeSTNeRF, to stylize the scene using texts via cross-modal learning: we leverage an advanced text encoder to embed the texts in order to control 3D style transfer and align the input text and output stylized images in latent space. |
JIAFU CHEN et. al. | ijcai | 2023-08-23 |
| 669 | Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID. |
JIANYANG GU et. al. | arxiv-cs.CV | 2023-08-21 |
| 670 | A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. |
Zhongliang Guo; Weiye Li; Yifei Qian; Ognjen Arandjelović; Lei Fang; | arxiv-cs.CV | 2023-08-17 |
| 671 | A White-Box False Positive Adversarial Attack Method on Contrastive Loss-Based Offline Handwritten Signature Verification Models IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. We propose a … |
Zhongliang Guo; Yifei Qian; Ognjen Arandjelovic; Lei Fang; | ArXiv | 2023-08-17 |
| 672 | Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced By Denoising Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, an image-click CAPTCHA scheme called Diff-CAPTCHA is proposed based on denoising diffusion models. |
Ran Jiang; Sanfeng Zhang; Linfeng Liu; Yanbing Peng; | arxiv-cs.CR | 2023-08-16 |
| 673 | CoDeF: Content Deformation Fields for Temporally Consistent Video Processing IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis. |
HAO OUYANG et. al. | arxiv-cs.CV | 2023-08-15 |
| 674 | Hierarchy Flow For High-Fidelity Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose Hierarchy Flow, a novel flow-based model to achieve better content preservation during translation. |
Weichen Fan; Jinghuan Chen; Ziwei Liu; | arxiv-cs.CV | 2023-08-13 |
| 675 | Zero-shot Text-driven Physically Interpretable Face Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a novel and physically interpretable method for face editing based on arbitrary text prompts. |
YAPENG MENG et. al. | arxiv-cs.CV | 2023-08-11 |
| 676 | A Forensic Methodology for Detecting Image Manipulations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this study, image file and mobile forensic artifacts analysis were conducted for detecting image manipulation. |
Jiwon Lee; Seungjae Jeon; Yunji Park; Jaehyun Chung; Doowon Jeong; | arxiv-cs.MM | 2023-08-09 |
| 677 | VAST: Vivify Your Talking Avatar Via Zero-Shot Expressive Facial Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes an unsupervised variational style transfer model (VAST) to vivify the neutral photo-realistic avatars. |
LIYANG CHEN et. al. | arxiv-cs.CV | 2023-08-09 |
| 678 | A Comparative Study of Image-to-Image Translation Using GANs for Synthetic Child Race Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work proposes the utilization of image-to-image transformation to synthesize data of different races and thus adjust the ethnicity of children’s face data. |
Wang Yao; Muhammad Ali Farooq; Joseph Lemley; Peter Corcoran; | arxiv-cs.CV | 2023-08-08 |
| 679 | DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose DiffSynth, a novel approach that aims to convert image synthesis pipelines to video synthesis pipelines. |
ZHONGJIE DUAN et. al. | arxiv-cs.CV | 2023-08-07 |
| 680 | Photorealistic and Identity-Preserving Image-Based Emotion Manipulation with Latent Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we investigate the emotion manipulation capabilities of diffusion models with in-the-wild images, a rather unexplored application area relative to the vast and rapidly growing literature for image-to-image translation tasks. |
Ioannis Pikoulis; Panagiotis P. Filntisis; Petros Maragos; | arxiv-cs.CV | 2023-08-06 |
| 681 | Diving Deeper Into Volume Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The Pando Thrower is a weapon of great importance in Disney’s Strange World. The explosive Pando fuel mixture is expelled with turbulent, fluid-like motion, with branching arcs … |
Mike Navarro; | ACM SIGGRAPH 2023 Talks | 2023-08-06 |
| 682 | Singed Silhouettes and Feed Forward Flames: Volumetric Neural Style Transfer for Expressive Fire Simulation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: While controlling simulated gaseous volumes remains an ongoing battle when seeking realism in computer graphics, creating appealing characters entirely out of these simulations … |
Paul Kanyuk; V. C. Azevedo; Raphael Ortiz; Jingwei Tang; | ACM SIGGRAPH 2023 Talks | 2023-08-06 |
| 683 | FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. |
ALLOY DAS et. al. | arxiv-cs.CV | 2023-08-05 |
| 684 | Superpixel-Based Style Transfer Method for Single-Temporal Remote Sensing Image Identification in Forest Type Groups Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Forests are the most important carbon reservoirs on land, and forest carbon sinks can effectively reduce atmospheric CO2 concentrations and mitigate climate change. In recent … |
Zhenyu Yu; Jinnian Wang; Xiankun Yang; Juan Ma; | Remote. Sens. | 2023-08-04 |
| 685 | MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In fact, each token of a text contains different style intensity and makes different contribution to the overall style. Our proposed method addresses this issue by assigning individual style vector to each token in a text, allowing for fine-grained control and manipulation of the style strength. |
Yazheng Yang; Zhou Zhao; Qi Liu; | kdd | 2023-08-04 |
| 686 | ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a novel framework to generate Accurate and Diverse Stylized Captions (ADS-Cap). |
KANZHI CHENG et. al. | arxiv-cs.CV | 2023-08-02 |
| 687 | ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. |
YASHENG SUN et. al. | arxiv-cs.CV | 2023-08-01 |
| 688 | Joint Image-to-Image Translation for Traffic Monitoring Driver Face Image Enhancement IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The real traffic monitoring driver face (TMDF) images are with complex multiple degradations, which decline face recognition accuracy in real intelligent transportation systems … |
CHANGHUI HU et. al. | IEEE Transactions on Intelligent Transportation Systems | 2023-08-01 |
| 689 | Controlling Geometric Abstraction and Texture for Artistic Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present a novel method for the interactive control of geometric abstraction and texture in artistic images. |
MARTIN BÜSSEMEYER et. al. | arxiv-cs.CV | 2023-07-31 |
| 690 | InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although effective, ignoring the clear disentanglement of the content features and the style features from the first beginning, they have difficulty in balancing between content preservation and style transferring. To tackle this problem, we propose a novel information disentanglement method, named InfoStyler, to capture the minimal sufficient information for both content and style representations from the pre-trained encoding network. |
Yueming Lyu; Yue Jiang; Bo Peng; Jing Dong; | arxiv-cs.CV | 2023-07-30 |
| 691 | The Generation of Articulatory Animations Based on Keypoint Detection and Motion Transfer Combined with Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Knowing the correct positioning of the tongue and mouth for pronunciation is crucial for learning English pronunciation correctly. Articulatory animation is an effective way to … |
Xufeng Ling; Yu Zhu; W. Liu; Jingxin Liang; Jie Yang; | Comput. | 2023-07-28 |
| 692 | CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for A Disentangled, Interpretable and Controllable Text-Guided Face Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Disentanglement, interpretability, and controllability are also hard to guarantee for manipulation. To alleviate these problems, we propose to define corpus subspaces spanned by relevant prompts to capture specific image characteristics. |
Chenliang Zhou; Fangcheng Zhong; Cengiz Öztireli; | siggraph | 2023-07-26 |
| 693 | On The Fly Neural Style Smoothing for Risk-Averse Domain Generalization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To enable risk-averse predictions from a DG classifier, we propose a novel inference procedure, Test-Time Neural Style Smoothing (TT-NSS), that uses a style-smoothed version of the DG classifier for prediction at test time. |
Akshay Mehra; Yunbei Zhang; Bhavya Kailkhura; Jihun Hamm; | arxiv-cs.CV | 2023-07-17 |
| 694 | Unsupervised Domain Adaption for Remote Sensing Semantic Segmentation with Self-Attention Mechanism Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The domain shift between the source and target domains limits the performance of traditional convolutional neural networks (CNNs) for feature extraction in remote sensing tasks. … |
Keming Liu; Fang Liu; Jia Liu; Liang Xiao; Xu Tang; | IGARSS 2023 – 2023 IEEE International Geoscience and Remote … | 2023-07-16 |
| 695 | Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Considering the difficulties in transferring highly structural patterns on the garments and discontinuous poses, existing methods often generate unsatisfactory results such as distorted textures and flickering artifacts. To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer. |
WING-YIN YU et. al. | arxiv-cs.CV | 2023-07-15 |
| 696 | Sem-CS: Semantic CLIPStyler for Text-Based Image Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, the ground semantics of objects in the style transfer output is lost due to style spill-over on salient and background objects (content mismatch) or over-stylization. To solve this, we propose Semantic CLIPStyler (Sem-CS), that performs semantic style transfer. |
Chanda Grover Kamra; Indra Deep Mastan; Debayan Gupta; | arxiv-cs.CV | 2023-07-12 |
| 697 | Substance or Style: What Does Your Image Embedding Know? Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in … |
CYRUS RASHTCHIAN et. al. | ArXiv | 2023-07-10 |
| 698 | DIFF-NST: Diffusion Interleaving For DeFormable Neural Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: With the recent introduction of diffusion models, such as Stable Diffusion, we can access far more powerful image generation techniques, enabling new possibilities. In our work, we propose using this new class of models to perform style transfer while enabling deformable style transfer, an elusive capability in previous models. |
DAN RUTA et. al. | arxiv-cs.CV | 2023-07-09 |
| 699 | Text Style Transfer Back-Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: For natural inputs, BT brings only slight improvements and sometimes even adverse effects. To address this issue, we propose Text Style Transfer Back Translation (TST BT), which uses a style transfer to modify the source side of BT data. |
DAIMENG WEI et. al. | acl | 2023-07-08 |
| 700 | PEIT: Bridging The Modality Gap with Pre-trained Models for End-to-End Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose PEIT, an end-to-end image translation framework that bridges the modality gap with pre-trained models. |
Shaolin Zhu; Shangjie Li; Yikun Lei; Deyi Xiong; | acl | 2023-07-08 |
| 701 | Artistic Image Style Transfer Based on CycleGAN Network Model Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the development of computer technology, image stylization has become one of the hottest technologies in image processing. To optimize the effect of artistic image style … |
Yanxi Wei; | Int. J. Image Graph. | 2023-07-07 |
| 702 | Dual-task Attention-guided Character Image Generation Method Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Human body pose transfer is to transform the character image from the source image pose to the target pose. In recent years, the research has achieved great success in … |
Fang Zhang; Hongjuan Wang; Lukun Wang; Yue Wang; | Journal of Intelligent & Fuzzy Systems | 2023-07-03 |
| 703 | A Compact Transformer for Adaptive Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Due to the limitation of spatial receptive field, it is challenging for CNN-based style transfer methods to capture rich and long-range semantic concepts in artworks. Though the … |
Yi Li; Xinxiong Xie; Haiyan Fu; Xiangyang Luo; Yanqing Guo; | 2023 IEEE International Conference on Multimedia and Expo … | 2023-07-01 |
| 704 | Point Cloud-Based Free Viewpoint Artistic Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In recent years, artistic style transfer has gained popularity as a means of creating visually appealing images by injecting style into the content image. Although various methods … |
Eun-Gyeong Bae; Jaekyung Kim; Sanghoon Lee; | 2023 IEEE International Conference on Multimedia and Expo … | 2023-07-01 |
| 705 | Rendering and Reconstruction Based 3D Portrait Stylization Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Both 2D images and 3D models are vital aspects of portrait applications. Existing style transfer methods principally emphasized 2D images, neglecting the urge for 3D style … |
Shaoxu Li; Ye Pan; | 2023 IEEE International Conference on Multimedia and Expo … | 2023-07-01 |
| 706 | StyleStegan: Leak-free Style Transfer Based on Feature Steganography Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, thereby hindering the further propagation of stylized images in social networks. To address this problem, we propose a leak-free style transfer method based on feature steganography. |
Xiujian Liang; Bingshan Liu; Qichao Ying; Zhenxing Qian; Xinpeng Zhang; | arxiv-cs.CV | 2023-07-01 |
| 707 | PCFN: Progressive Cross-Modal Fusion Network for Human Pose Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The goal of human pose transfer is to transfer the human in the image from the original pose to the desired one. Existing methods utilizing progressive manner have achieved great … |
Wei Yu; Yanping Li; Rui Wang; W. Cao; Wei Xiang; | IEEE Transactions on Circuits and Systems for Video … | 2023-07-01 |
| 708 | Ship Detection in Low-Quality SAR Images Via An Unsupervised Domain Adaption Method Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Ship detection in low-quality Synthetic Aperture Radar (SAR) images poses a persistent challenge. Noise signals in complex environments disrupt imaging conditions, hindering SAR … |
Xinyang Pu; He Jia; Yu Xin; Feng Wang; Haipeng Wang; | Remote. Sens. | 2023-06-29 |
| 709 | SinDDM: A Single Image Denoising Diffusion Model IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Here, we introduce a framework for training a DDM on a single image. |
Vladimir Kulikov; Shahar Yadin; Matan Kleiner; Tomer Michaeli; | icml | 2023-06-27 |
| 710 | User-Controllable Arbitrary Style Transfer Via Entropy Regularization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel solution ensuring both efficiency and diversity for generating multiple user-controllable AST results by systematically modulating AST behavior at run-time. |
JIAXIN CHENG et. al. | aaai | 2023-06-26 |
| 711 | Progressive Energy-Based Cooperative Learning for Multi-Domain Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Since the style generator is represented as an domain-specific distribution of style codes, the translator can provide a one-to-many transformation (i.e., diversified generation) between source domain and target domain. To train our framework, we propose a likelihood-based multi-domain cooperative learning algorithm to jointly train the multi-domain descriptor and the diversified image generator (including translator, style encoder, and style generator modules) via multi-domain MCMC teaching, in which the descriptor guides the diversified image generator to shift its probability density toward the data distribution, while the diversified image generator uses its randomly translated images to initialize the descriptor’s Langevin dynamics process for efficient sampling. |
Weinan Song; Yaxuan Zhu; Lei He; Yingnian Wu; Jianwen Xie; | arxiv-cs.CV | 2023-06-26 |
| 712 | Preserving Structural Consistency in Arbitrary Artist and Artwork Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These methods not only homogenize the artist-style of different artworks of the same artist but also lack generalization for the unseen artists. To solve these challenges, we propose a double-style transferring module (DSTM). |
JINGYU WU et. al. | aaai | 2023-06-26 |
| 713 | SHUNIT: Style Harmonization for Unpaired Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a novel solution for unpaired image-to-image (I2I) translation. |
Seokbeom Song; Suhyeon Lee; Hongje Seong; Kyoungwon Min; Euntai Kim; | aaai | 2023-06-26 |
| 714 | CodeStylist: A System for Performing Code Style Transfer Using Neural Networks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Code style refers to attributes of computer programs that affect their readability, maintainability, and performance. Enterprises consider code style as important and enforce … |
CHIH-KAI TING et. al. | AAAI Conference on Artificial Intelligence | 2023-06-26 |
| 715 | Practical Disruption of Image Translation Deepfake Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work we propose Leaking Transferable Perturbations (LTP), an algorithm that significantly reduces the number of queries needed to disrupt an image translation network by dynamically re-purposing previous disruptions into new query efficient disruptions. |
Nataniel Ruiz; Sarah Adel Bargal; Cihang Xie; Stan Sclaroff; | aaai | 2023-06-26 |
| 716 | Frequency Domain Disentanglement for Arbitrary Neural Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. |
DONGYANG LI et. al. | aaai | 2023-06-26 |
| 717 | MicroAST: Towards Super-fast Ultra-Resolution Arbitrary Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources, which heavily hinders their further applications. In this paper, we tackle this dilemma by learning a straightforward and lightweight model, dubbed MicroAST. |
ZHIZHONG WANG et. al. | aaai | 2023-06-26 |
| 718 | AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-Realistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose the Adaptive ColorMLP (AdaCM), an effective and efficient framework for universal photo-realistic style transfer. |
TIANWEI LIN et. al. | aaai | 2023-06-26 |
| 719 | PP-GAN : Style Transfer from Korean Portraits to ID Photos Using Landmark Extractor with GAN Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Owing to its distinct characteristics from the hair in ID photos, transferring the Gat is challenging. To address this issue, this study proposes a deep learning network that can perform style transfer, including the Gat, while preserving the identity of the face. |
Jongwook Si; Sungyoung Kim; | arxiv-cs.CV | 2023-06-23 |
| 720 | What to Learn: Features, Image Transformations, or Both? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose to combine an image transformation network and a feature-learning network to improve long-term localization performance. |
Yuxuan Chen; Binbin Xu; Frederike Dümbgen; Timothy D. Barfoot; | arxiv-cs.RO | 2023-06-22 |
| 721 | A Neurally Guided Patch-Based Style Transfer for Mobile Devices Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Style transfer is an application that has increased interest, primarily because of the impressive results obtained using neural networks. However, this application demands a lot … |
J. I. S. SILVA et. al. | 2023 International Joint Conference on Neural Networks … | 2023-06-18 |
| 722 | LisaCLIP: Locally Incremental Semantics Adaptation Towards Zero-shot Text-driven Image Synthesis Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The automatic transfer of a plain photo into a desired synthetic style has attracted numerous users in the application fields of photo editing, visual art, and entertainment. By … |
An Cao; Yilin Zhou; Gang Shen; | 2023 International Joint Conference on Neural Networks … | 2023-06-18 |
| 723 | ArtFusion: Controllable Arbitrary Style Transfer Using Dual Conditional Latent Diffusion Models Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: Arbitrary Style Transfer (AST) aims to transform images by adopting the style from any selected artwork. Nonetheless, the need to accommodate diverse and subjective user … |
Da Chen; | ArXiv | 2023-06-15 |
| 724 | Motion Capture Dataset for Practical Use of AI-based Motion Editing and Stylization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we proposed a new style-diverse dataset for the domain of motion style transfer. |
Makito Kobayashi; Chen-Chieh Liao; Keito Inoue; Sentaro Yojima; Masafumi Takahashi; | arxiv-cs.CV | 2023-06-15 |
| 725 | ArtFusion: Arbitrary Style Transfer Using Dual Conditional Latent Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a new approach, ArtFusion, which provides a flexible balance between content and style. |
Dar-Yen Chen; | arxiv-cs.CV | 2023-06-15 |
| 726 | GBSD: Generative Bokeh with Stage Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present GBSD, the first generative text-to-image model that synthesizes photorealistic images with a bokeh style. |
Jieren Deng; Xin Zhou; Hao Tian; Zhihong Pan; Derek Aguiar; | arxiv-cs.CV | 2023-06-14 |
| 727 | GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we introduce a novel versatile framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), that improves the quality, applicability and controllability of the existing translation models. |
Shuai Yang; Liming Jiang; Ziwei Liu; Chen Change Loy; | arxiv-cs.CV | 2023-06-07 |
| 728 | Improving Diffusion-based Image Translation Using Asymmetric Gradient Guidance Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Yet, these methods often require computationally intense fine-tuning of diffusion models or additional neural networks. To address these challenges, here we present an approach that guides the reverse process of diffusion sampling by applying asymmetric gradient guidance. |
Gihyun Kwon; Jong Chul Ye; | arxiv-cs.CV | 2023-06-07 |
| 729 | Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a new TTS system that can perform style transfer with interpretability and high fidelity. |
WENHAO GUAN et. al. | arxiv-cs.SD | 2023-06-07 |
| 730 | A Conditional GAN Architecture for Colorization of Thermal Infrared Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The applicability of visible spectrum cameras is limited to nighttime and extreme weather conditions. To overcome these limitations, infrared (IR) cameras were introduced, but … |
Ekaagra Dubey; N. Singh; Prateek Joshi; R. Prasad; | 2023 IEEE World AI IoT Congress (AIIoT) | 2023-06-07 |
| 731 | Identifying The Style By A Qualified Reader on A Short Fragment of Generated Poetry Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: I used 3 character-based LSTM-models to work with style reproducing assessment. |
Boris Orekhov; | arxiv-cs.CL | 2023-06-05 |
| 732 | Instruct-Video2Avatar: Video-to-Avatar Generation with Instructions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a method for synthesizing edited photo-realistic digital avatars with text instructions. |
Shaoxu Li; | arxiv-cs.CV | 2023-06-05 |
| 733 | Name Your Style: Text-guided Artistic Style Transfer IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image style transfer has attracted widespread attention in the past years. Despite its remarkable results, it requires additional style images available as references, making it … |
Zhi-Song Liu; Li-Wen Wang; W. Siu; Vicky Kalogeiton; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 734 | Image Reference-guided Fashion Design with Structure-aware Transfer By Diffusion Models IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-based fashion design with AI techniques has attracted increasing attention in recent years. We focus on a new fashion design task, where we aim to transfer a reference … |
Shidong Cao; Wenhao Chai; Shengyu Hao; Gaoang Wang; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 735 | DeSRF: Deformable Stylized Radiance Field IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: When stylizing 3D scenes, current methods need to render the full-resolution images from different views and use the style loss, which is proposed for 2D style transfer and needs … |
Shiyao Xu; Lingzhi Li; Li Shen; Z. Lian; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 736 | Diffusion-Enhanced PatchMatch: A Framework for Arbitrary Style Transfer with Diffusion Models IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Diffusion models have gained immense popularity in recent years due to their impressive ability to generate high-quality images. The opportunities that diffusion models provide … |
Mark Hamazaspyan; Shant Navasardyan; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 737 | Unsupervised Bidirectional Style Transfer Network Using Local Feature Transform Module Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we propose a bidirectional style transfer method by exchanging the style of inputs while preserving the structural information. The proposed bidirectional style … |
K. Bae; Hyungil Kim; Y. Kwon; Jinyoung Moon; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 738 | Gatha: Relational Loss for Enhancing Text-based Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text-based style transfer is a promising area of research that enables the generation of stylistic images from plain text descriptions. However, the existing text-based style … |
Surgan Jandial; Shripad Deshmukh; Abhinav Java; Simra Shahid; Balaji Krishnamurthy; | 2023 IEEE/CVF Conference on Computer Vision and Pattern … | 2023-06-01 |
| 739 | SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-guided Video Editing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the … |
Nazmul Karim; Umar Khalid; M. Joneidi; Chen Chen; N. Rahnavard; | ArXiv | 2023-05-30 |
| 740 | Simulation-Aided Deep Learning for Laser Ultrasonic Visualization Testing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In recent years, laser ultrasonic visualization testing (LUVT) has attracted much attention because of its ability to efficiently perform non-contact ultrasonic non-destructive … |
Miya Nakajima; T. Saitoh; Tsuyoshi Kato; | ArXiv | 2023-05-30 |
| 741 | Context-Preserving Two-Stage Video Domain Translation for Portrait Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the issue, we propose a novel two-stage video translation framework with an objective function which enforces a model to generate a temporally coherent stylized video while preserving context in the source video. |
DOYEON KIM et. al. | arxiv-cs.CV | 2023-05-30 |
| 742 | SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Although the latter is computationally less expensive, it still takes a significant amount of time for per-video adaption. To address this issue, we propose SAVE, a novel spectral-shift-aware adaptation framework, in which we fine-tune the spectral shift of the parameter space instead of the parameters themselves. |
Nazmul Karim; Umar Khalid; Mohsen Joneidi; Chen Chen; Nazanin Rahnavard; | arxiv-cs.CV | 2023-05-29 |
| 743 | Conditional Score Guidance for Text-Driven Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. |
Hyunsoo Lee; Minsoo Kang; Bohyung Han; | arxiv-cs.CV | 2023-05-29 |
| 744 | StyleS2ST: Zero-shot Style Transfer for Direct Speech-to-speech Translation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Direct speech-to-speech translation (S2ST) has gradually become popular as it has many advantages compared with cascade S2ST. However, current research mainly focuses on the … |
KUN SONG et. al. | arxiv-cs.SD | 2023-05-28 |
| 745 | Image Style Transfer Based on Cyclegan Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Generative Adversarial Networks (GAN) have powerful adversarial learning capabilities and are currently being used by more and more researchers. The style transfer of images is an … |
Lisha Yao; Qiaoqiao Feng; | 2023 IEEE 3rd International Conference on Electronic … | 2023-05-26 |
| 746 | CLIP3Dstyler: Language Guided 3D Arbitrary Neural Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). |
MING GAO et. al. | arxiv-cs.CV | 2023-05-25 |
| 747 | SAMScore: A Semantic Structural Similarity Metric for Image Translation Evaluation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness. … |
YUNXIANG LI et. al. | ArXiv | 2023-05-24 |
| 748 | SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Traditional image-level similarity metrics are of limited use, since the content structures of an image are high-level, and not strongly governed by pixel-wise faithfulness to an original image. To fill this gap, we introduce SAMScore, a generic content structural similarity metric for evaluating the faithfulness of image translation models. |
YUNXIANG LI et. al. | arxiv-cs.CV | 2023-05-24 |
| 749 | Variational Bayesian Framework for Advanced Image Generation with Domain-Related Variables Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, it remains challenging for existing methods to address advanced conditional generative problems without annotations, which can enable multiple applications like image-to-image translation and image editing. We present a unified Bayesian framework for such problems, which introduces an inference stage on latent variables within the learning process. |
Yuxiao Li; Santiago Mazuelas; Yuan Shen; | arxiv-cs.CV | 2023-05-23 |
| 750 | InstructVid2Vid: Controllable Video Editing with Natural Language Instructions IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce InstructVid2Vid, an end-to-end diffusion-based methodology for video editing guided by human language instructions. |
Bosheng Qin; Juncheng Li; Siliang Tang; Tat-Seng Chua; Yueting Zhuang; | arxiv-cs.CV | 2023-05-20 |
| 751 | Brain Captioning: Decoding Human Brain Activity Into Images and Text IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Recent breakthroughs in functional magnetic resonance imaging (fMRI) have enabled scientists to extract visual information from human brain activity patterns. In this study, we present an innovative method for decoding brain activity into meaningful images and captions, with a specific focus on brain captioning due to its enhanced flexibility as compared to brain decoding into images. |
Matteo Ferrante; Furkan Ozcelik; Tommaso Boccato; Rufin VanRullen; Nicola Toschi; | arxiv-cs.CV | 2023-05-19 |
| 752 | Drag Your GAN: Interactive Point-based Manipulation on The Generative Image Manifold IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we study a powerful yet much less explored way of controlling GANs, that is, to drag any points of the image to precisely reach target points in a user-interactive manner, as shown in Fig.1. |
XINGANG PAN et. al. | arxiv-cs.CV | 2023-05-18 |
| 753 | Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose a domain adaptive Sim-to-Real framework called IoU-Ranking Blend-ArtFlow (IRB-AF) for image segmentation of oropharyngeal organs. |
Guankun Wang; Tian-Ao Ren; Jiewen Lai; Long Bai; Hongliang Ren; | arxiv-cs.AI | 2023-05-18 |
| 754 | CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper proposes a new framework named CAP-VSTNet, which consists of a new reversible residual network and an unbiased linear transform module, for versatile style transfer. |
Linfeng Wen; Chengying Gao; Changqing Zou; | cvpr | 2023-05-17 |
| 755 | Imagic: Text-Based Real Image Editing With Diffusion Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-based semantic edits to a single real image. |
BAHJAT KAWAR et. al. | cvpr | 2023-05-17 |
| 756 | Modernizing Old Photos Using Multiple References Via Photorealistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In order to modernize old photos, we propose a novel multi-reference-based old photo modernization (MROPM) framework consisting of a network MROPM-Net and a novel synthetic data generation scheme. |
Agus Gunawan; Soo Ye Kim; Hyeonjun Sim; Jae-Ho Lee; Munchurl Kim; | cvpr | 2023-05-17 |
| 757 | Masked and Adaptive Transformer for Exemplar Based Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present a novel framework for exemplar based image translation. |
CHANG JIANG et. al. | cvpr | 2023-05-17 |
| 758 | Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present a new framework that takes text-to-image synthesis to the realm of image-to-image translation — given a guidance image and a target text prompt as input, our method harnesses the power of a pre-trained text-to-image diffusion model to generate a new image that complies with the target text, while preserving the semantic layout of the guidance image. |
Narek Tumanyan; Michal Geyer; Shai Bagon; Tali Dekel; | cvpr | 2023-05-17 |
| 759 | BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model(BBDM) is proposed, which models image-to-image translation as a stochastic Brownian Bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process. |
Bo Li; Kaitao Xue; Bin Liu; Yu-Kun Lai; | cvpr | 2023-05-17 |
| 760 | Inversion-Based Style Transfer With Diffusion Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Specifically, we perceive style as a learnable textual description of a painting.We propose an inversion-based style transfer method (InST), which can efficiently and accurately learn the key information of an image, thus capturing and transferring the artistic style of a painting. |
YUXIN ZHANG et. al. | cvpr | 2023-05-17 |
| 761 | Tunable Convolutions With Parametric Multi-Loss Optimization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we propose to optimize a parametric tunable convolutional layer, which includes a number of different kernels, using a parametric multi-loss, which includes an equal number of objectives. |
Matteo Maggioni; Thomas Tanay; Francesca Babiloni; Steven McDonagh; Aleš Leonardis; | cvpr | 2023-05-17 |
| 762 | Neural Preset for Color Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed. |
Zhanghan Ke; Yuhao Liu; Lei Zhu; Nanxuan Zhao; Rynson W.H. Lau; | cvpr | 2023-05-17 |
| 763 | Transforming Radiance Field With Lipschitz Network for Photorealistic 3D Scene Stylization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Simply coupling NeRF with photorealistic style transfer (PST) will result in cross-view inconsistency and degradation of stylized view syntheses. Through a thorough analysis, we demonstrate that this non-trivial task can be simplified in a new light: When transforming the appearance representation of a pre-trained NeRF with Lipschitz mapping, the consistency and photorealism across source views will be seamlessly encoded into the syntheses. |
ZICHENG ZHANG et. al. | cvpr | 2023-05-17 |
| 764 | Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we devise a novel Transformer model termed as Master specifically for style transfer. |
HAO TANG et. al. | cvpr | 2023-05-17 |
| 765 | StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose StyleRF (Style Radiance Fields), an innovative 3D style transfer technique that resolves the three-way dilemma by performing style transformation within the feature space of a radiance field. |
KUNHAO LIU et. al. | cvpr | 2023-05-17 |
| 766 | Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Current 3D scene stylization methods transfer textures and colors as styles using arbitrary style references, lacking meaningful semantic correspondences. We introduce Reference-Based Non-Photorealistic Radiance Fields (Ref-NPR) to address this limitation. |
Yuechen Zhang; Zexin He; Jinbo Xing; Xufeng Yao; Jiaya Jia; | cvpr | 2023-05-17 |
| 767 | Learning Dynamic Style Kernels for Artistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To further enhance the flexibility of our style transfer method, we propose a Style Alignment Encoding (SAE) module complemented with a Content-based Gating Modulation (CGM) module for learning the dynamic style kernels in focusing regions. |
Wenju Xu; Chengjiang Long; Yongwei Nie; | cvpr | 2023-05-17 |
| 768 | EDICT: Exact Diffusion Inversion Via Coupled Transformations IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, DDIM inversion for real images is unstable as it relies on local linearization assumptions, which result in the propagation of errors, leading to incorrect image reconstruction and loss of content. To alleviate these problems, we propose Exact Diffusion Inversion via Coupled Transformations (EDICT), an inversion method that draws inspiration from affine coupling layers. |
Bram Wallace; Akash Gokul; Nikhil Naik; | cvpr | 2023-05-17 |
| 769 | Wavelet-based Unsupervised Label-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired data to accomplish this task while generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and learn correspondences in appearance instead of semantic content. Starting from the assumption that a high quality generated image should be segmented back to its semantic layout, we propose a new Unsupervised paradigm for SIS (USIS) that makes use of a self-supervised segmentation loss and whole image wavelet based discrimination. |
George Eskandar; Mohamed Abdelsamad; Karim Armanious; Shuai Zhang; Bin Yang; | arxiv-cs.CV | 2023-05-16 |
| 770 | Style Transfer Enabled Sim2Real Framework for Efficient Learning of Robotic Ultrasound Image Analysis Using Simulated Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work presents a Sim2Real framework to efficiently learn robotic US image analysis tasks based only on simulated data for real-world deployment. |
KEYU LI et. al. | arxiv-cs.RO | 2023-05-16 |
| 771 | Realization RGBD Image Stylization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel method that incorporates the depth map and a heatmap of the RGB image to generate more realistic style transfer results. |
Bhavya Sehgal; Vaishnavi Mendu; Aparna Mendu; | arxiv-cs.CV | 2023-05-11 |
| 772 | Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper proposes a zero-shot video stylization method named Style-A-Video, which utilizes a generative pre-trained transformer with an image latent diffusion model to achieve a concise text-controlled video stylization. |
Nisha Huang; Yuxin Zhang; Weiming Dong; | arxiv-cs.CV | 2023-05-09 |
| 773 | Joint Multi-scale Cross-lingual Speaking Style Transfer with Bidirectional Attention Mechanism for Automatic Dubbing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a joint multi-scale cross-lingual speaking style transfer framework to simultaneously model the bidirectional speaking style transfer between languages at both global (i.e. utterance level) and local (i.e. word level) scales. |
JINGBEI LI et. al. | arxiv-cs.SD | 2023-05-09 |
| 774 | Joint Multiscale Cross-Lingual Speaking Style Transfer With Bidirectional Attention Mechanism for Automatic Dubbing Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Automatic dubbing, which generates a corresponding version of the input speech in another language, can be widely utilized in many real-world scenarios, such as video and game … |
JINGBEI LI et. al. | IEEE/ACM Transactions on Audio, Speech, and Language … | 2023-05-09 |
| 775 | Multi-Teacher Knowledge Distillation For Text Image Machine Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a novel Multi-Teacher Knowledge Distillation (MTKD) method to effectively distillate knowledge into the end-to-end TIMT model from the pipeline model. |
CONG MA et. al. | arxiv-cs.CL | 2023-05-09 |
| 776 | HRInversion: High-Resolution GAN Inversion for Cross-Domain Image Synthesis IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: We investigate GAN inversion problems of using pre-trained GANs to reconstruct real images. Recent methods for such problems typically employ a VGG perceptual loss to measure the … |
Peng Zhou; Lingxi Xie; Bingbing Ni; Lin Liu; Qi Tian; | IEEE Transactions on Circuits and Systems for Video … | 2023-05-01 |
| 777 | Duetcs: Code Style Transfer Through Generation and Retrieval Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Coding style has direct impact on code comprehension. Automatically transferring code style to user’s preference or consistency can facilitate project cooperation and maintenance, … |
Binger Chen; Ziawasch Abedjan; | 2023 IEEE/ACM 45th International Conference on Software … | 2023-05-01 |
| 778 | Image Neural Style Transfer: A Review IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Qiang Cai; Mengxu Ma; Chen Wang; Haisheng Li; | Comput. Electr. Eng. | 2023-05-01 |
| 779 | Transplayer: Timbre Style Transfer with Flexible Timbre Control IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the practice in voice conversion, we propose TransPlayer, which uses an autoencoder model with one-hot representations of instruments as the condition, and a Diffwave model trained especially for music synthesis. |
Y. Wu; Y. He; X. Liu; Y. Wang; R. B. Dannenberg; | icassp | 2023-04-27 |
| 780 | MSNet: A Deep Architecture Using Multi-Sentiment Semantics for Sentiment-Aware Image Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To incorporate the sentiment information into the image style transfer task for better sentiment-aware performance, we introduce a new task named sentiment-aware image style transfer. |
S. Sun; J. Jia; H. Wu; Z. Ye; J. Xing; | icassp | 2023-04-27 |
| 781 | CPD-GAN: Cascaded Pyramid Deformation GAN for Pose Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing work often failed to transfer complex textures to generated images well. To solve this problem, we propose a novel network for this task. |
Y. Huang; Y. Tang; X. Zheng; J. Tang; | icassp | 2023-04-27 |
| 782 | Multidimensional Evaluation for Text Style Transfer Using ChatGPT IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We perform a comprehensive correlation analysis for two transfer directions (and overall) at different levels. |
Huiyuan Lai; Antonio Toral; Malvina Nissim; | arxiv-cs.CL | 2023-04-26 |
| 783 | Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To mitigate those limitations, we propose Hierarchical Diffusion Autoencoders (HDAE) that exploit the fine-grained-to-abstract and lowlevel-to-high-level feature hierarchy for the latent space of diffusion models. |
ZEYU LU et. al. | arxiv-cs.CV | 2023-04-24 |
| 784 | Unsupervised Style-based Explicit 3D Face Reconstruction from Single Image Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a general adversarial learning framework for solving Unsupervised 2D to Explicit 3D Style Transfer (UE3DST). |
Heng Yu; Zoltan A. Milacski; Laszlo A. Jeni; | arxiv-cs.CV | 2023-04-24 |
| 785 | Aesthetic Style Transferring Method Based on Deep Neural Network Between Chinese Landscape Painting and Classical Private Garden’s Virtual Scenario IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Most of the existing virtual scenarios built for the digital protection of Chinese classical private gardens are too modern in expression style to show the aesthetic significance … |
SHUAI HONG et. al. | International Journal of Digital Earth | 2023-04-23 |
| 786 | Arbitrary Style Transfer with Multiple Self-Attention Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Style transfer aims to transfer the style information of a given style image to the other images, but most existing methods cannot transfer the texture details in style images … |
Yuzhu Song; Li Liu; Huaxiang Zhang; Dongmei Liu; Hongzhen Li; | Proceedings of the 2023 8th International Conference on … | 2023-04-21 |
| 787 | A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel plug-and-play invisible copyright protection method based on defensive perturbation for DNN-based applications (i.e., style transfer). |
DONGHUA WANG et. al. | arxiv-cs.CV | 2023-04-20 |
| 788 | Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In either case, only one result can be generated for a specific pair of content and style images, which therefore lacks flexibility and is hard to satisfy different users with different preferences. We propose here a novel strategy termed Any-to-Any Style Transfer to address this drawback, which enables users to interactively select styles of regions in the style image and apply them to the prescribed content regions. |
Songhua Liu; Jingwen Ye; Xinchao Wang; | arxiv-cs.CV | 2023-04-19 |
| 789 | UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: The appearance inconsistency makes T2I unsuitable for pose transfer. We address this by proposing a multimodal diffusion model that accepts text, pose, and visual prompting. |
Soon Yau Cheong; Armin Mustafa; Andrew Gilbert; | arxiv-cs.CV | 2023-04-18 |
| 790 | ALADIN-NST: Self-supervised Disentangled Representation Learning of Artistic Style Through Neural Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our paper aims to learn a representation of visual artistic style more strongly disentangled from the semantic content depicted in an image. |
Dan Ruta; Gemma Canet Tarres; Alexander Black; Andrew Gilbert; John Collomosse; | arxiv-cs.CV | 2023-04-12 |
| 791 | Improving Diffusion Models for Scene Text Editing with Dual Encoders IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, our empirical analysis reveals that state-of-the-art diffusion models struggle with rendering correct text and controlling text style. To address these problems, we propose DIFFSTE to improve pre-trained diffusion models with a dual encoder design, which includes a character encoder for better text legibility and an instruction encoder for better style control. |
JIABAO JI et. al. | arxiv-cs.CV | 2023-04-11 |
| 792 | Panoramic Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we tackle the challenging task of Panoramic Image-to-Image translation (Pano-I2I) for the first time. |
SOOHYUN KIM et. al. | arxiv-cs.CV | 2023-04-11 |
| 793 | NeAT: Neural Artistic Tracing for Beautiful Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present NeAT, a new state-of-the art feed-forward style transfer method. |
Dan Ruta; Andrew Gilbert; John Collomosse; Eli Shechtman; Nicholas Kolkin; | arxiv-cs.CV | 2023-04-11 |
| 794 | DDRF: Denoising Diffusion Model for Remote Sensing Image Fusion IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, … |
ZIHAN CAO et. al. | ArXiv | 2023-04-10 |
| 795 | ITportrait: Image-Text Coupled 3D Portrait Domain Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose an Image-Text multi-modal framework, namely Image and Text portrait (ITportrait), for 3D portrait domain adaptation. |
XIANGWEN DENG et. al. | arxiv-cs.MM | 2023-04-09 |
| 796 | SAM-GAN: Supervised Learning-Based Aerial Image-to-Map Translation Via Generative Adversarial Networks IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Accurate translation of aerial imagery to maps is a direction of great value and challenge in mapping, a method of generating maps that does not require using vector data as … |
Jian Xu; Xiaowen Zhou; Chaolin Han; Bing Dong; Hongwei Li; | ISPRS Int. J. Geo Inf. | 2023-04-07 |
| 797 | Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Generative Adversarial Networks with style-based generators could successfully synthesize realistic images from input latent code. Moreover, recent studies have revealed that … |
Yunfan Liu; Qi Li; Qiyao Deng; Zhenan Sun; | IEEE Transactions on Circuits and Systems for Video … | 2023-04-01 |
| 798 | A CNN Inference Accelerator on FPGA With Compression and Layer-Chaining Techniques for Style Transfer Applications IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, convolutional neural networks (CNNs) have actively been applied to computer vision applications such as style transfer that changes the style of a content image into … |
SUCHANG KIM et. al. | IEEE Transactions on Circuits and Systems I: Regular Papers | 2023-04-01 |
| 799 | Fake Colorized Image Detection Based on Special Image Representation and Transfer Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Nowadays, images have become one of the most popular forms of communication as image editing tools have evolved. Image manipulation, particularly image colorization, has become … |
Khalid A. Salman; Khalid Shaker; Sufyan T. Faraj Al-Janabi; | Int. J. Comput. Intell. Appl. | 2023-04-01 |
| 800 | Unpaired Image-to-image Translation of Structural Damage IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Subin Varghese; Vedhus Hoskere; | Adv. Eng. Informatics | 2023-04-01 |
| 801 | One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Departing from the common notion of transferring only the target “texture” information, we leverage text-to-image diffusion models (e.g., Stable Diffusion) to generate a synthetic target dataset with photo-realistic images that not only faithfully depict the style of the target domain, but are also characterized by novel scenes in diverse contexts. |
Yasser Benigmim; Subhankar Roy; Slim Essid; Vicky Kalogeiton; Stéphane Lathuilière; | arxiv-cs.CV | 2023-03-31 |
| 802 | Semantic Image Translation for Repairing The Texture Defects of Building Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In order to preserve fine details and regular structures, we propose a regularity-aware multi-domain method that capitalizes on frequency information and corner maps. |
QISEN SHANG et. al. | arxiv-cs.CV | 2023-03-30 |
| 803 | Instant Photorealistic Neural Radiance Fields Stylization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present Instant Neural Radiance Fields Stylization, a novel approach for multi-view image stylization for the 3D scene. |
Shaoxu Li; Ye Pan; | arxiv-cs.CV | 2023-03-29 |
| 804 | Depth-Aware Neural Style Transfer for Videos Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Temporal consistency and content preservation are the prominent challenges in artistic video style transfer. To address these challenges, we present a technique that utilizes … |
E. Ioannou; S. Maddock; | Comput. | 2023-03-27 |
| 805 | Linear-ResNet GAN-based Anime Style Transfer of Face Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Mingxi Chen; Hansen Dai; Shijie Wei; Zhenzhen Hu; | Signal, Image and Video Processing | 2023-03-23 |
| 806 | Neural Preset for Color Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed. |
Zhanghan Ke; Yuhao Liu; Lei Zhu; Nanxuan Zhao; Rynson W. H. Lau; | arxiv-cs.CV | 2023-03-23 |
| 807 | Open-World Pose Transfer Via Sequential Test-Time Adaption Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A typical pose transfer framework usually employs representative datasets to train a discriminative model, which is often violated by out-of-distribution (OOD) instances. |
JUNYANG CHEN et. al. | arxiv-cs.CV | 2023-03-20 |
| 808 | StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose StyleRF (Style Radiance Fields), an innovative 3D style transfer technique that resolves the three-way dilemma by performing style transformation within the feature space of a radiance field. |
KUNHAO LIU et. al. | arxiv-cs.CV | 2023-03-19 |
| 809 | Multi-scale Attention Enhancement for Arbitrary Style Transfer Via Contrast Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Arbitrary style transfer is to transfer any artistic style to the content image while preserving the content structure as much as possible. Although there is currently a lot of … |
Lei Zhou; Taotao Zhang; | Proceedings of the 2023 9th International Conference on … | 2023-03-17 |
| 810 | Style Transfer for 2D Talking Head Animation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present a new method to generate talking head animation with learnable style references. |
TRONG-THANG PHAM et. al. | arxiv-cs.CV | 2023-03-17 |
| 811 | DialogPaint: A Dialog-based Image Editing Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce DialogPaint, a novel framework that bridges conversational interactions with image editing, enabling users to modify images through natural dialogue. |
Jingxuan Wei; Shiyu Wu; Xin Jiang; Yequan Wang; | arxiv-cs.CV | 2023-03-17 |
| 812 | NLUT: Neural-based 3D Lookup Tables for Video Photorealistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, existing methods obtain stylized video sequences by performing frame-by-frame photorealistic style transfer, which is inefficient and does not ensure the temporal consistency of the stylized video. To address this issue, we use neural network-based 3D Lookup Tables (LUTs) for the photorealistic transfer of videos, achieving a balance between efficiency and effectiveness. |
YAOSEN CHEN et. al. | arxiv-cs.CV | 2023-03-16 |
| 813 | SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from A Spectral Perspective Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose SpectralCLIP, which implements a spectral filtering layer on top of the CLIP vision encoder, to alleviate the artifact issue. |
Zipeng Xu; Songlong Xing; Enver Sangineto; Nicu Sebe; | arxiv-cs.CV | 2023-03-16 |
| 814 | StylerDALLE: Language-Guided Style Transfer Using A Vector-Quantized Tokenizer of A Large-Scale Generative Model IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, these abstract semantics can be captured by models like DALL-E or CLIP, which have been trained using huge datasets of images and textual documents. In this paper, we propose StylerDALLE, a style transfer method that exploits both of these models and uses natural language to describe abstract art styles. |
Zipeng Xu; Enver Sangineto; Nicu Sebe; | arxiv-cs.CV | 2023-03-16 |
| 815 | Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce and implement a model which combines image-to-image and class-guided denoising diffusion probabilistic models. |
JAN OSCAR CROSS-ZAMIRSKI et. al. | arxiv-cs.CV | 2023-03-15 |
| 816 | 3D Face Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, previous methods mainly use images of artistic faces for style transfer while ignoring arbitrary style images such as abstract paintings. To solve this problem, we propose a novel method, namely Face-guided Dual Style Transfer (FDST). |
XIANGWEN DENG et. al. | arxiv-cs.CV | 2023-03-14 |
| 817 | PADAAV: Enhancing Perception Systems Using GAN-generated Adversarial Augmented Domains for Autonomous Vehicles Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the field of autonomous vehicles (AV), it is crucial for the perceptual systems of the AVs to learn inter-domain adaptations in the absence of paired examples for detecting … |
Oshin Rawlley; Shashank Gupta; | 2023 IEEE International Conference on Pervasive Computing … | 2023-03-13 |
| 818 | SEM-CS: Semantic CLIPStyler for Text-Based Image Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, the ground semantics of objects in style transfer output is lost due to style spillover on salient and background objects (content mismatch) or over-stylization. To solve this, we propose Semantic CLIPStyler (Sem-CS) that performs semantic style transfer. |
Chanda G Kamra; Indra Deep Mastan; Debayan Gupta; | arxiv-cs.CV | 2023-03-11 |
| 819 | AptSim2Real: Approximately-Paired Sim-to-Real Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unpaired image translation, while more suitable for sim-to-real transfer, is still challenging to learn for complex natural scenes. To address these challenges, we propose a third category: approximately-paired sim-to-real translation, where the source and target images do not need to be exactly paired. |
Charles Y Zhang; Ashish Shrivastava; | arxiv-cs.CV | 2023-03-09 |
| 820 | A Unified Arbitrary Style Transfer Framework Via Adaptive Contrastive Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style transfer models, e.g., CNN-based, ViT-based, and flow-based methods. |
YUXIN ZHANG et. al. | arxiv-cs.CV | 2023-03-08 |
| 821 | End-to-end Face-swapping Via Adaptive Latent Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper proposes a novel and end-to-end integrated framework for high resolution and attribute preservation face swapping via Adaptive Latent Representation Learning. |
Chenhao Lin; Pengbin Hu; Chao Shen; Qian Li; | arxiv-cs.CV | 2023-03-07 |
| 822 | Neural Style Transfer for Vector Graphics Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: Neural style transfer draws researchers’ attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and … |
V. Efimova; Artyom Chebykin; Ivan Jarsky; Evgenii Prosvirnin; A. Filchenkov; | ArXiv | 2023-03-06 |
| 823 | Guided Image-to-Image Translation By Discriminator-Generator Communication Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This formulation illustrates the information insufficiency in the GAN training. To mitigate this problem, we propose to add a communication channel between discriminators and generators. |
Yuanjiang Cao; Lina Yao; Le Pan; Quan Z. Sheng; Xiaojun Chang; | arxiv-cs.CV | 2023-03-06 |
| 824 | Stylized Image Denoising Via Noise Style Transfer and Quasi Siamese Network Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Jikang Cheng; Zhen Han; Zhongyuan Wang; | Signal Process. Image Commun. | 2023-03-01 |
| 825 | Cross-modal Face- and Voice-style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a cross-modal style transfer framework called XFaVoT that jointly learns four tasks: image translation and voice conversion tasks with audio or image guidance, which enables the generation of “face that matches given voice and “voice that matches given face, and intra-modality translation tasks with a single framework. |
Naoya Takahashi; Mayank K. Singh; Yuki Mitsufuji; | arxiv-cs.CV | 2023-02-27 |
| 826 | Multi-Modal Multi-Stage Underwater Side-Scan Sonar Target Recognition Based on Synthetic Images IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Due to the small sample size of underwater acoustic data and the strong noise interference caused by seabed reverberation, recognizing underwater targets in Side-Scan Sonar (SSS) … |
Jian Wang; Haisen S. Li; Guanying Huo; Chao Li; Yuhang Wei; | Remote. Sens. | 2023-02-26 |
| 827 | ACE: Zero-Shot Image to Image Translation Via Pretrained Auto-Contrastive-Encoder Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, learning such mapping between domains is challenging because data from different domains can be highly unbalanced in terms of both quality and quantity. To address this problem, we propose a new approach to extract image features by learning the similarities and differences of samples within the same data distribution via a novel contrastive learning framework, which we call Auto-Contrastive-Encoder (ACE). |
Sihan Xu; Zelong Jiang; Ruisi Liu; Kaikai Yang; Zhijie Huang; | arxiv-cs.CV | 2023-02-22 |
| 828 | Paint It Black: Generating Paintings from Text Descriptions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the intersection of these two, i.e., generating paintings from a given caption, is a relatively unexplored area with little data available. In this paper, we have explored two distinct strategies and have integrated them together. |
Mahnoor Shahid; Mark Koch; Niklas Schneider; | arxiv-cs.CV | 2023-02-17 |
| 829 | Conversation Style Transfer Using Few-Shot Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel in-context learning approach to solve the task with style-free dialogues as a pivot. |
SHAMIK ROY et. al. | arxiv-cs.CL | 2023-02-16 |
| 830 | DiffFashion: Reference-based Fashion Design with Structure-aware Transfer By Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Although diffusion-based image translation or neural style transfer (NST) has enabled flexible style transfer, it is often difficult to maintain the original structure of the image realistically during the reverse diffusion, especially when the referenced appearance image greatly differs from the common clothing appearance. To tackle this issue, we present a novel diffusion model-based unsupervised structure-aware transfer method to semantically generate new clothes from a given clothing image and a reference appearance image. |
SHIDONG CAO et. al. | arxiv-cs.CV | 2023-02-13 |
| 831 | Unified Vision-Language Representation Modeling for E-Commerce Same-Style Products Retrieval IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Common methods use the image as the detected object, but they only consider the visual features and overlook the attribute information contained in the textual descriptions, and perform weakly for products in image less important industries like machinery, hardware tools and electronic component, even if an additional text matching module is added. In this paper, we propose a unified vision-language modeling method for e-commerce same-style products retrieval, which is designed to represent one product with its textual descriptions and visual contents. |
BEN CHEN et. al. | arxiv-cs.IR | 2023-02-10 |
| 832 | Neural Artistic Style Transfer with Conditional Adversaria Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present two methods that step toward the style image independent neural style transfer model. |
P. N. Deelaka; | arxiv-cs.CV | 2023-02-07 |
| 833 | Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Besides, existing methods are mainly based on test-time optimization or fine-tuning model for each input image, which are extremely time-consuming for practical applications. To address these issues, we propose a new approach for flexible image translation by learning a layout-aware image condition together with a text condition. |
Shiqi Sun; Shancheng Fang; Qian He; Wei Liu; | arxiv-cs.CV | 2023-02-04 |
| 834 | ReDi: Efficient Learning-Free Diffusion Inference Via Trajectory Retrieval IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To accelerate the inference, we propose ReDi, a simple yet learning-free Retrieval-based Diffusion sampling framework. |
Kexun Zhang; Xianjun Yang; William Yang Wang; Lei Li; | arxiv-cs.CV | 2023-02-04 |
| 835 | Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present rectified flow, a simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributions $\pi_0$ and $\pi_1$, hence providing a unified solution to generative modeling and domain transfer, among various other tasks involving distribution transport. |
Xingchao Liu; Chengyue Gong; qiang liu; | iclr | 2023-02-01 |
| 836 | Enhancing Image Representation in Conditional Image Synthesis Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Even though deep neural network-based conditional image synthesis has shown impressive advances in terms of image quality, they still fall short of dealing with domain-dependent … |
Jong-Chae Shim; Eunbeen Kim; Hyeonwoo Kim; E. Hwang; | 2023 IEEE International Conference on Big Data and Smart … | 2023-02-01 |
| 837 | Extremal Domain Translation with Neural Optimal Transport IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Inspired by the recent advances in neural optimal transport (OT), we propose a scalable algorithm to approximate ET maps as a limit of partial OT maps. |
Milena Gazdieva; Alexander Korotin; Daniil Selikhanovych; Evgeny Burnaev; | arxiv-cs.LG | 2023-01-30 |
| 838 | Edge-guided Multi-domain RGB-to-TIR Image Translation for Training Vision Tasks with Challenging Labels IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: As a remedy, we propose a modified multidomain RGB to TIR image translation model focused on edge preservation to employ annotated RGB images with challenging labels. |
Dong-Guw Lee; Myung-Hwan Jeon; Younggun Cho; Ayoung Kim; | arxiv-cs.CV | 2023-01-30 |
| 839 | ITstyler: Image-optimized Text-based Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we achieve a data-efficient text-based style transfer method that does not require optimization at the inference stage. |
Yunpeng Bai; Jiayue Liu; Chao Dong; Chun Yuan; | arxiv-cs.CV | 2023-01-25 |
| 840 | A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Inspired by the features of FilmSet images, we propose a novel framework called FilmNet based on Laplacian Pyramid for stylizing images across frequency bands and achieving film style outcomes. |
Zinuo Li; Xuhang Chen; Shuqiang Wang; Chi-Man Pun; | arxiv-cs.CV | 2023-01-20 |
| 841 | Acoustic Camera Pose Refinement Using Differentiable Rendering Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Acoustic cameras, also known as 2D forward looking sonars, show high reliability in underwater environments as they can produce high resolution images even if the illumination is … |
CHUJIE WU et. al. | 2023 IEEE/SICE International Symposium on System … | 2023-01-17 |
| 842 | Image-to-Image Translation with Disentangled Latent Vectors for Face Editing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an image-to-image translation framework for facial attribute editing with disentangled interpretable latent directions. |
Yusuf Dalva; Hamza Pehlivan; Cansu Moran; Öykü Irmak Hatipoğlu; Ayşegül Dündar; | arxiv-cs.CV | 2023-01-11 |
| 843 | Tackling Data Bias in Painting Classification with Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a system to handle data bias in small paintings datasets like the Kaokore dataset while simultaneously accounting for domain adaptation in fine-tuning a model trained on real world images. |
Mridula Vijendran; Frederick W. B. Li; Hubert P. H. Shum; | arxiv-cs.CV | 2023-01-06 |
| 844 | FAEC‐GAN: An Unsupervised Face‐to‐anime Translation Based on Edge Enhancement and Coordinate Attention Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Animation is a widely loved artistic form with high abstraction and powerful expression. The task of image translation from face to anime involves complex geometric and texture … |
Hong Lin; Chenchen Xu; Chun Liu; | Computer Animation and Virtual Worlds | 2023-01-03 |
| 845 | Edge Enhanced Image Style Transfer Via Transformers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To stylize the image with sufficient style patterns, the content details may be damaged and sometimes the objects of images can not be distinguished clearly. For this reason, we present a new transformer-based method named STT for image style transfer and an edge loss which can enhance the content details apparently to avoid generating blurred results for excessive rendering on style features. |
Chiyu Zhang; Jun Yang; Zaiyan Dai; Peng Cao; | arxiv-cs.CV | 2023-01-02 |
| 846 | Interactive Control Over Temporal Consistency While Stylizing Video Streams Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that stylizes video streams in real-time at full HD resolutions while providing interactive consistency control. |
SUMIT SHEKHAR et. al. | arxiv-cs.GR | 2023-01-02 |
| 847 | Fine-Grained Face Editing Via Personalized Spatial-Aware Affine Modulation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Fine-grained face editing, as a special case of image translation task, aims at modifying face attributes according to users’ preference. Although generative adversarial networks … |
SI LIU et. al. | IEEE Transactions on Multimedia | 2023-01-01 |
| 848 | Is Bigger Always Better? An Empirical Study on Efficient Architectures for Style Transfer and Beyond Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Network architecture plays a pivotal role in style transfer. Most existing algorithms use VGG19 as the feature extractor, which incurs a high computational cost. In this work, we … |
Jie An; Tao Li; Haozhi Huang; Jinwen Ma; Jiebo Luo; | 2023 IEEE/CVF Winter Conference on Applications of Computer … | 2023-01-01 |
| 849 | Side-Scan Sonar Image Simulation Considering Imaging Mechanism and Marine Environment for Zero-Shot Shipwreck Detection IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In the process of side-scan sonar (SSS) image target detection and recognition, the direct application of deep learning techniques will cause serious overfitting due to the … |
Zhao Xi; Jianhu Zhao; Weiqiang Zhu; | IEEE Transactions on Geoscience and Remote Sensing | 2023-01-01 |
| 850 | Bimodal Neural Style Transfer for Image Generation Based on Text Prompts Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Diego Gutiérrez; Marcelo Mendoza; | Interacción | 2023-01-01 |
| 851 | P$^{2}$-GAN: Efficient Stroke Style Transfer Using Single Style Image Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Style transfer is a useful image synthesis technique that can re-render given image into another artistic style while preserving its content information. Generative Adversarial … |
Zhentan Zheng; Jianyi Liu; Nanning Zheng; | IEEE Transactions on Multimedia | 2023-01-01 |
| 852 | InkGAN: Generative Adversarial Networks for Ink-And-Wash Style Transfer of Photographs Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this work, we present a novel approach for Chinese Ink-and-Wash style transfer using a GAN structure. The proposed method incorporates a specially designed smooth loss tailored … |
KEYI YU et. al. | Adv. Artif. Intell. Mach. Learn. | 2023-01-01 |
| 853 | Enhancing Style-Guided Image-to-Image Translation Via Self-Supervised Metric Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: There has been significant success in recent image-to-image translation (I2I) approaches in translating the source image into the style of the target image. Existing techniques … |
Qi Mao; Siwei Ma; | IEEE Transactions on Multimedia | 2023-01-01 |
| 854 | ICDaeLST: Intensity-Controllable Detail Attention-enhanced for Lightweight Fast Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The mainstream style transfer methods usually use pre-trained deep convolutional neural network (VGG) models as encoders, or use more complex model structures to achieve better … |
Jiang Shi Qi; | ArXiv | 2023-01-01 |
| 855 | GAN Architecture Leveraging A Retinex Model With Colored Illumination for Low-Light Image Restoration Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this work, we study the restoration of text low-light images with outdoor scenes without ground truth. Until now, approaches in the literature have avoided using the Retinex … |
Arthur Lecert; A. Roumy; R. Fraisse; C. Guillemot; | IEEE Access | 2023-01-01 |
| 856 | Application of Artificial Intelligence-based Style Transfer Algorithm in Animation Special Effects Design Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Today, the rapid development of computer technology changes with each passing day. In the computer field, computer animation has rapidly grown from a new thing to a leading … |
Shan Li; | Open Computer Science | 2023-01-01 |
| 857 | StyleAdapter: A Single-Pass LoRA-Free Model for Stylized Image Generation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This paper presents a LoRA-free method for stylized image generation that takes a text prompt and style reference images as inputs and produces an output image in a single pass. … |
ZHOUXIA WANG et. al. | ArXiv | 2023-01-01 |
| 858 | ACE-HetEM for Ab Initio Heterogenous Cryo-EM 3D Reconstruction Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Due to the extremely low signal-to-noise ratio (SNR) and unknown poses (projection angles and image translation) in cryo-EM experiments, reconstructing 3D structures from 2D … |
Weijie Chen; Lin Yao; Zeqing Xia; Yuhang Wang; | ArXiv | 2023-01-01 |
| 859 | Optimal Transport-Based Patch Matching for Image Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: State-of-the-art image style transfer methods have achieved impressive results by using neural networks. However, neural style transfer (NST) methods either ignore the local … |
Jie Li; Yong Xiang; Hao Wu; Shao-qing Yao; Dan Xu; | IEEE Transactions on Multimedia | 2023-01-01 |
| 860 | Training-free Style Transfer Emerges from H-space in Diffusion Models IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Diffusion models (DMs) synthesize high-quality images in various domains. However, controlling their generative process is still hazy because the intermediate variables in the … |
Jaeseok Jeong; Mingi Kwon; Youngjung Uh; | ArXiv | 2023-01-01 |
| 861 | MS-SST: Single Image Reconstruction-Based Stain-Style Transfer for Multi-Domain Hematoxylin & Eosin Stained Pathology Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In digital pathology, pathological tissue images that are obtained using scanners are analyzed and diseases are diagnosed. One crucial aspect of this process is the staining of … |
Juwon Kweon; Mujung Kim; Gilly Yun; Soon-chul Kwon; Jisang Yoo; | IEEE Access | 2023-01-01 |
| 862 | Augment CAPTCHA Security Using Adversarial Examples With Neural Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: To counteract rising bots, many CAPTCHAs (Completely Automated Public Turing tests to tell Computers and Humans Apart) have been developed throughout the years. Automated attacks, … |
Nghia Dinh; Kiet Tran-Trung; Vinh Truong Hoang; | IEEE Access | 2023-01-01 |
| 863 | MFSANet: Zero-Shot Side-Scan Sonar Image Recognition Based on Style Transfer IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Side-scan sonar (SSS) is attracting increasing attention in ocean exploration for its utility and stability on autonomous underwater vehicles (AUVs). Existing SSS image … |
Hongli Xu; Zhongyu Bai; X. Zhang; Qichuan Ding; | IEEE Geoscience and Remote Sensing Letters | 2023-01-01 |
| 864 | Text-Guided Image Manipulation Via Generative Adversarial Network With Referring Image Segmentation-Based Guidance Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This study proposes a novel text-guided image manipulation method that introduces referring image segmentation into a generative adversarial network. The proposed text-guided … |
Yuto Watanabe; Ren Togo; Keisuke Maeda; Takahiro Ogawa; M. Haseyama; | IEEE Access | 2023-01-01 |
| 865 | Synthetic Driver Image Generation for Human Pose-Related Tasks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: : The interest in driver monitoring has grown recently, especially in the context of autonomous vehicles. However, the training of deep neural networks for computer vision … |
Romain Guesdon; C. Crispim; Laure Tougne Rodet; | VISIGRAPP | 2023-01-01 |
| 866 | SAMStyler: Enhancing Visual Creativity With Neural Style Transfer and Segment Anything Model (SAM) IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Neural Style Transfer (NST) is a popular technique of computer vision where the content of an image is blended with the style of another, which results in a fused image with … |
KONSTANTINOS PSYCHOGYIOS et. al. | IEEE Access | 2023-01-01 |
| 867 | Treatment Learning Causal Transformer for Noisy Image Classification Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Current top-notch deep learning (DL) based vision models are primarily based on exploring and exploiting the inherent correlations between training data samples and their … |
C. Yang; I-Te Danny Hung; Yi-Chieh Liu; Pin-Yu Chen; | 2023 IEEE/CVF Winter Conference on Applications of Computer … | 2023-01-01 |
| 868 | A Novel Human Image Sequence Synthesis Method By Pose-Shape-Content Inference Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In online clothing sales, static model images only describe specific clothing statuses towards consumers. Without increasing shooting costs, it is a subject to display clothing … |
N. FANG et. al. | IEEE Transactions on Multimedia | 2023-01-01 |
| 869 | Facial Expression Transfer Based on Conditional Generative Adversarial Networks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the development of computer vision and image transfer, facial expression transfer has been more and more widespread applications. But there are still some problems, such as … |
Yang Fan; Xingguo Jiang; Shuxing. Lan; Jianghai Lan; | IEEE Access | 2023-01-01 |
| 870 | Recent Advances in Text-to-Image Synthesis: Approaches, Datasets and Future Research Prospects IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text-to-image synthesis is a fascinating area of research that aims to generate images based on textual descriptions. The main goal of this field is to generate images that match … |
YONG XUAN TAN et. al. | IEEE Access | 2023-01-01 |
| 871 | Eliminating Adversarial Perturbations Using Image-to-Image Translation Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Haibo Zhang; Zhihua Yao; Kouichi Sakurai; | ACNS Workshops | 2023-01-01 |
| 872 | Arbitrary Style Transfer With Fused Convolutional Block Attention Modules Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The advancement of deep learning has rendered image style transfer a progressively intricate subject matter. The proposed solution aims to tackle the limitations of current … |
H. Xin; L. Li; | IEEE Access | 2023-01-01 |
| 873 | Style Transfer of Thangka Images Highlighting Style Attributes Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The HAA-GAN (Highlighting Artistic Attributes Generative Adversarial Net-work) style migration model is proposed to address the problem of poor expression of image artistic … |
Wenjin Hu; Huafei Song; Fujun Zhang; Yinqiu Zhao; Xinyue Shi; | IEEE Access | 2023-01-01 |
| 874 | Image and Video Style Transfer Based on Transformer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The essence of image style transfer is to generate images that both maintain in the original content image and present the effect with artistic features under the guidance of … |
FENGXUE SUN et. al. | IEEE Access | 2023-01-01 |
| 875 | Neural Style Transfer for Image-Based Garment Interchange Through Multi-Person Human Views IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: : The generation of photorealistic images of human appearances under the guidance of body pose enables a wide range of applications, including virtual fitting and style synthesis. … |
Hajer Ghodhbani; Mohamed Neji; A. Alimi; | VISIGRAPP | 2023-01-01 |
| 876 | TwinGAN: Twin Generative Adversarial Network for Chinese Landscape Painting Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, style transfers have received considerable attention. However, most of these studies were suitable for Western paintings. In this paper, a deep learning method is … |
Der-Lor Way; Chang-Hao Lo; Yueqing Wei; Zen-Chung Shih; | IEEE Access | 2023-01-01 |
| 877 | Sim-to-Real Transfer for Object Detection in Aerial Inspections of Transmission Towers Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Training deep learning models for object detection usually requires a large amount of data, a condition that is not common for most real-world applications, especially in the … |
AUGUSTO J. PETERLEVITZ et. al. | IEEE Access | 2023-01-01 |
| 878 | Disentangled Representation for Cross-Domain Medical Image Segmentation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image segmentation is a long-standing problem in medical image analysis to facilitate the clinical diagnosis and intervention. Progress has been made due to deep learning via … |
JIEXI WANG et. al. | IEEE Transactions on Instrumentation and Measurement | 2023-01-01 |
| 879 | Intelligent Typography: Artistic Text Style Transfer for Complex Texture and Structure IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text style transfer is an important task to render artistic texts from a reference image or style, and is widely desired in many visual creations. Previous works have brought some … |
W. Mao; Shuai Yang; Huihong Shi; Jiaying Liu; Zhongfeng Wang; | IEEE Transactions on Multimedia | 2023-01-01 |
| 880 | RAST: Restorable Arbitrary Style Transfer Via Multi-restoration IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Abstract: Arbitrary style transfer aims to reproduce the target image with the artistic or photo-realistic styles provided. Even though existing approaches can successfully transfer style … |
Yingnan Ma; Chenqiu Zhao; Anup Basu; Xudong Li; | 2023 IEEE/CVF Winter Conference on Applications of Computer … | 2023-01-01 |
| 881 | Vehicle Detection at Night Based on Style Transfer Image Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Jianing Shen; Rong Li; | J. Inf. Process. Syst. | 2023-01-01 |
| 882 | Style-Content-Aware Adaptive Normalization Based Pose Guided for Person Image Synthesis Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Most of the tasks based on pose-guided person image synthesis have obtained accurate target pose, but still have not obtained reasonable style texture mapping. In this paper, we … |
Wei Wei; Xiao Yang; Xiaodong Duan; Chen Guo; | IEEE Access | 2023-01-01 |
| 883 | Modeling of Reptile Search Algorithm With Deep Learning Approach for Copy Move Image Forgery Detection IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Copy-move (CM) forgery is a common type of image manipulation that involves copying and pasting a region within an image to conceal or duplicate content. Detection of such … |
M. MAASHI et. al. | IEEE Access | 2023-01-01 |
| 884 | Face-PAST: Facial Pose Awareness and Style Transfer Networks Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Facial style transfer has been quite popular among researchers due to the rise of emerging technologies such as eXtended Reality (XR), Metaverse, and Non-Fungible Tokens (NFTs). … |
Sunder Ali Khowaja; Ghulam Mujtaba; Jiseok Yoon; I. Lee; | ArXiv | 2023-01-01 |
| 885 | Unsupervised Text Style Transfer Through Differentiable Back Translation and Rewards Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Dibyanayan Bandyopadhyay; Asif Ekbal; | Pacific-Asia Conference on Knowledge Discovery and Data … | 2023-01-01 |
| 886 | Accelerating Neural Style-Transfer Using Contrastive Learning for Unsupervised Satellite Image Super-Resolution IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Contrastive learning is a self-supervised comparison of two samples to identify characteristics and traits that distinguish one data class from another, improving performance on … |
Divya Mishra; O. Hadar; | IEEE Transactions on Geoscience and Remote Sensing | 2023-01-01 |
| 887 | Exploiting Style Transfer and Semantic Segmentation to Facilitate Infrared and Visible Image Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Hsing-Wei Chang; Po-Chyi Su; Si Ting Lin; | International Conference on Technologies and Applications … | 2023-01-01 |
| 888 | A Hybrid Artistic Model Using Deepy-Dream Model and Multiple Convolutional Neural Networks Architectures IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The significant increase in drug abuse cases prompts developers to investigate techniques that mimic the hallucinations imagined by addicts and abusers, in addition to the … |
Lafta R. Al-khazraji; A. Abbas; A. S. Jamil; A. Hussain; | IEEE Access | 2023-01-01 |
| 889 | Unsupervised Embroidery Generation Using Embroidery Channel Attention Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: It is a challenging task to synthesize an embroidery image with complex texture from a colorful image. Existing style transfer methods to synthesize embroidery images will lead to … |
CHEN YANG et. al. | Proceedings of the 18th ACM SIGGRAPH International … | 2022-12-27 |
| 890 | Scaling Painting Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper provides a solution to solve the original global optimization for ultra-high resolution (UHR) images, enabling multiscale NST at unprecedented image sizes. |
Bruno Galerne; Lara Raad; José Lezama; Jean-Michel Morel; | arxiv-cs.CV | 2022-12-27 |
| 891 | Arbitrary Style Transfer with Semantic Content Enhancement Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Arbitrary style transfer is an import topic which changes the style of a source image according to a reference one. It is useful for artistic creation and intelligent imaging … |
GUOSHUAI LI et. al. | Proceedings of the 18th ACM SIGGRAPH International … | 2022-12-27 |
| 892 | DSI2I: Dense Style for Unpaired Image-to-Image Translation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Here, in contrast, we propose to represent style as a dense feature map, allowing for a finer-grained transfer to the source image without requiring any external semantic information. |
Baran Ozaydin; Tong Zhang; Sabine Süsstrunk; Mathieu Salzmann; | arxiv-cs.CV | 2022-12-26 |
| 893 | Meta-Learning for Color-to-Infrared Cross-Modal Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis reveals that existing data-driven methods are either too simplistic or introduce significant artifacts into the imagery. To overcome these limitations, we propose meta-learning style transfer (MLST), which learns a stylization by composing and tuning well-behaved analytic functions. |
Evelyn A. Stump; Francesco Luzi; Leslie M. Collins; Jordan M. Malof; | arxiv-cs.CV | 2022-12-24 |
| 894 | Artistic Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite all the efforts, it’s still a major challenge to apply the artistic style that was originally created on top of the structure of the content image while maintaining consistency. In this work, we solved these problems by using a Deep Learning approach using Convolutional Neural Networks. |
Weiting Li; Rahul Vyas; Ramya Sree Penta; | arxiv-cs.CV | 2022-12-21 |
| 895 | QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we devise a new style transfer framework called QuantArt for high visual-fidelity stylization. |
Siyu Huang; Jie An; Donglai Wei; Jiebo Luo; Hanspeter Pfister; | arxiv-cs.CV | 2022-12-20 |
| 896 | StyleTRF: Stylizing Tensorial Radiance Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF. |
Rahul Goel; Sirikonda Dhawal; Saurabh Saini; P. J. Narayanan; | arxiv-cs.CV | 2022-12-19 |
| 897 | ColoristaNet for Photorealistic Video Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To avoid employing the popular Gram loss, we propose a self-supervised style transfer framework, which contains a style removal part and a style restoration part. |
XIAOWEN QIU et. al. | arxiv-cs.CV | 2022-12-18 |
| 898 | Detecting Paralysis of Stroke Symptom in Video: Transfer Learning with Gated Recurrent Unit Using Public Big Data of Facial Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: This paper proposes transfer learning with spatiotemporal feature analysis using public facial images to build an automatic detection of facial paralysis caused by acute stroke. … |
Sohee Ban; H. Nam; Eunjeong Park; | 2022 IEEE International Conference on Big Data (Big Data) | 2022-12-17 |
| 899 | Deep Image Style Transfer from Freeform Text Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper creates a novel method of deep neural style transfer by generating style images from freeform user text input. |
Tejas Santanam; Mengyang Liu; Jiangyue Yu; Zhaodong Yang; | arxiv-cs.CV | 2022-12-13 |
| 900 | Zero-Shot Font Style Transfer with A Differentiable Renderer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, a large-scale language-image multi-modal model, CLIP, has been used to realize language-based image translation in a zero-shot manner without training. In this study, we … |
Kota Izumi; Keiji Yanai; | Proceedings of the 4th ACM International Conference on … | 2022-12-13 |
| 901 | Sonar Image Target Detection Based on Style Transfer Learning and Random Shape of Noise Under Zero Shot Target IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: With the development of sonar technology, sonar images have been widely used to detect targets. However, there are many challenges for sonar images in terms of object detection. … |
Jier Xi; Xiufen Ye; Chuanlong Li; | Remote. Sens. | 2022-12-10 |
| 902 | StyleTRF: Stylizing Tensorial Radiance Fields✱ Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Stylized view generation of scenes captured casually using a camera has received much attention recently. The geometry and appearance of the scene are typically captured as neural … |
Rahul Goel; Dhawal Sirikonda; Saurabh Saini; P J Narayanan; | Proceedings of the Thirteenth Indian Conference on Computer … | 2022-12-08 |
| 903 | A Fast Texture-to-Stain Adversarial Stain Normalization Network for Histopathological Images Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Histopathological images, as the gold standard for cancer diagnosis, record abundant information about microscopic structures and morphological characteristics through staining … |
Qi Jia; Jing Guo; Fei Du; Peng Yang; Yun Yang; | 2022 IEEE International Conference on Bioinformatics and … | 2022-12-06 |
| 904 | Single-Modality Endoscopic Polyp Segmentation Via Random Color Reversal Synthesis and Two-Branched Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Endoscopic polyp segmentation plays a fundamental role in the diagnosis and treatment of colorectal cancer. However, polyp segmentation often suffers from limited accuracy due to … |
MINGZHU CHEN et. al. | 2022 IEEE International Conference on Bioinformatics and … | 2022-12-06 |
| 905 | Progressive Domain Translation Defogging Network for Real-World Fog Images IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Images captured in bad weather are affected by atmospheric scattering. To remove image degradation caused by scattering, many defogging methods have been proposed. However, due to … |
Q. Guo; Mingliang Zhou; | IEEE Transactions on Broadcasting | 2022-12-01 |
| 906 | Reference Based Sketch Extraction Via Attention Mechanism IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: We propose a model that extracts a sketch from a colorized image in such a way that the extracted sketch has a line style similar to a given reference sketch while preserving the … |
Amirsaman Ashtari; Chang Wook Seo; C. Kang; Sihun Cha; Jun-yong Noh; | ACM Transactions on Graphics (TOG) | 2022-11-30 |
| 907 | Neural Photo-Finishing IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image processing pipelines are ubiquitous and we rely on them either directly, by filtering or adjusting an image post-capture, or indirectly, as image signal processing (ISP) … |
ETHAN TSENG et. al. | ACM Transactions on Graphics (TOG) | 2022-11-30 |
| 908 | Interactive Image Manipulation with Complex Text Instructions Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recently, text-guided image manipulation has received increasing attention in the research field of multimedia processing and computer vision due to its high flexibility and … |
Ryugo Morita; Zhiqiang Zhang; Man M. Ho; Jinjia Zhou; | 2023 IEEE/CVF Winter Conference on Applications of Computer … | 2022-11-25 |
| 909 | Structure-aware Video Style Transfer with Map Art Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Changing the style of an image/video while preserving its content is a crucial criterion to access a new neural style transfer algorithm. However, it is very challenging to … |
T. Le; Ya-Hsuan Chen; Tong-Yee Lee; | ACM Transactions on Multimedia Computing, Communications … | 2022-11-23 |
| 910 | Touch and Go: Learning from Human-Collected Vision and Touch IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a dataset with paired visual and tactile data called Touch and Go, in which human data collectors probe objects in natural environments using tactile sensors, while simultaneously recording egocentric video. |
FENGYU YANG et. al. | arxiv-cs.CV | 2022-11-22 |
| 911 | LISA: Localized Image Stylization with Audio Via Implicit Neural Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a novel framework, Localized Image Stylization with Audio (LISA) which performs audio-driven localized image stylization. |
SEUNG HYUN LEE et. al. | arxiv-cs.CV | 2022-11-21 |
| 912 | DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we present DiffStyler on the basis of diffusion models. |
NISHA HUANG et. al. | arxiv-cs.CV | 2022-11-19 |
| 913 | Single Stage Multi-Pose Virtual Try-On Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel single stage model for MPVTON. |
Sen He; Yi-Zhe Song; Tao Xiang; | arxiv-cs.CV | 2022-11-19 |
| 914 | Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we present X-DualNet, a simple yet effective approach that enables unsupervised 3D pose transfer. |
Chaoyue Song; Jiacheng Wei; Ruibo Li; Fayao Liu; Guosheng Lin; | arxiv-cs.CV | 2022-11-18 |
| 915 | Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we propose a novel style guidance method to support generating images using arbitrary style guided by a reference image. |
Zhihong Pan; Xin Zhou; Hao Tian; | arxiv-cs.CV | 2022-11-14 |
| 916 | Learning Visual Representation of Underwater Acoustic Imagery Using Transformer-Based Style Transfer Method Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This letter proposed a framework for learning the visual representation of underwater acoustic imageries, which takes a transformer-based style transfer model as the main body. |
XIAOTENG ZHOU et. al. | arxiv-cs.CV | 2022-11-10 |
| 917 | Thermal-to-Color Image Translation for Enhancing Visual Odometry of Thermal Vision Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: A panoptic perception-based generative adversarial network for thermal-to-color image translation is proposed to demonstrate its potential as an image sequence enhancement for … |
Liyun Zhang; P. Ratsamee; Yuuki Uranishi; Manabu Higashida; H. Takemura; | 2022 IEEE International Symposium on Safety, Security, and … | 2022-11-08 |
| 918 | Generalized One-shot Domain Adaption of Generative Adversarial Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Besides, to realize cross-domain correspondence, we propose the variational Laplacian regularization to constrain the smoothness of the adapted generator. |
ZICHENG ZHANG et. al. | nips | 2022-11-06 |
| 919 | Dense Interspecies Face Embedding Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce a new task of cross-domain face understanding, and propose a dense interspecies face embedding (DIFE) learned in an unsupervised manner by our multi-teacher knowledge distillation and pseudo-paired data synthesis. |
Sejong Yang; Subin Jeon; Seonghyeon Nam; Seon Joo Kim; | nips | 2022-11-06 |
| 920 | Text-driven Photorealistic 3D Stylization For Arbitrary Meshes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Technically, we propose to disentangle the appearance style as the spatially varying bidirectional reflectance distribution function, the local geometric variation, and the lighting condition, which are jointly optimized, via supervision of the CLIP loss, by a spherical Gaussians based differentiable renderer. |
yongwei chen; chen rui; Jiabao Lei; Yabin Zhang; Kui Jia; | nips | 2022-11-06 |
| 921 | Facial Attribute Editing Based on Independent Selective Transfer Unit and Self-attention Mechanism Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Facial attribute editing aims to change the facial attributes, which can be regarded as an image translation problem. Facial attribute editing is usually realized by combining … |
XIAONING LIU et. al. | 2022 15th International Congress on Image and Signal … | 2022-11-05 |
| 922 | ConvUNeXt: A Lightweight Convolutional Neural Network for Watercolor Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-to-image transformation is the task of transforming an image from one domain to another. It includes the task of converting an image to an artistic style such as oil … |
Haoran Su; Jiamian Huang; Yasuaki Ito; K. Nakano; | 2022 Tenth International Symposium on Computing and … | 2022-11-01 |
| 923 | Generating Community Road Network from GPS Trajectories Via Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Road network generation from massive trajectories has mainly focused on the mining of urban arterial roads while the demand for refined road networks in communities full of … |
JIAWEI LI et. al. | Proceedings of the 30th International Conference on … | 2022-11-01 |
| 924 | Text-Only Training for Image Captioning Using Noise-Injected CLIP IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We consider the task of image-captioning using only the CLIP model and additional text data at training time, and no additional captioned images. |
David Nukrai; Ron Mokady; Amir Globerson; | arxiv-cs.CV | 2022-11-01 |
| 925 | Adaptive Affine Transformation: A Simple and Effective Operation for Spatial Misaligned Image Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Different from those dense flow based methods, we propose one simple but effective operator named AdaAT (Adaptive Affine Transformation) to realize misaligned image generation. |
Zhimeng Zhang; Yu Ding; | mm | 2022-10-30 |
| 926 | AI Illustrator: Translating Raw Descriptions Into Images By Prompt-based Cross-Modal Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: AI illustrator aims to automatically design visually appealing images for books to provoke rich thoughts and emotions. To achieve this goal, we propose a framework for translating raw descriptions with complex semantics into semantically corresponding images. |
Yiyang Ma; Huan Yang; Bei Liu; Jianlong Fu; Jiaying Liu; | mm | 2022-10-30 |
| 927 | Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Applications of deep-learning models in machine visions for crop/weed identification have remarkably upgraded the authenticity of precise weed management. However, compelling data … |
L. G. DIVYANTH et. al. | Algorithms | 2022-10-30 |
| 928 | Order-aware Human Interaction Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The majority of current techniques for pose transfer disregard the interactions between the transferred person and the surrounding instances, resulting in context inconsistency when applied to complicated situations. To tackle this issue, we propose InterOrderNet, a novel framework to perform order-aware interaction learning. |
Mandi Luo; Jie Cao; Ran He; | mm | 2022-10-30 |
| 929 | AesUST: Towards Aesthetic-Enhanced Universal Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, existing approaches suffer from the aesthetic-unrealistic problem that introduces disharmonious patterns and evident artifacts, making the results easy to spot from real paintings. To address this limitation, we propose AesUST, a novel Aesthetic-enhanced Universal Style Transfer approach that can generate aesthetically more realistic and pleasing results for arbitrary styles. |
ZHIZHONG WANG et. al. | mm | 2022-10-30 |
| 930 | Photorealistic Style Transfer Via Adaptive Filtering and Channel Seperation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: It is mainly caused by the interference between color and texture during transferring. To address this problem, we propose a end-to-end network via adaptive filtering and channel separation. |
HONG DING et. al. | mm | 2022-10-30 |
| 931 | Few-shot Image Generation Using Discrete Content Representation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we make the first attempt to adapt few-shot image translation method to few-shot image generation task. |
Yan Hong; Li Niu; Jianfu Zhang; Liqing Zhang; | mm | 2022-10-30 |
| 932 | MagicMix: Semantic Mixing with Diffusion Models IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Have you ever imagined what a corgi-alike coffee machine or a tiger-alike rabbit would look like? In this work, we attempt to answer these questions by exploring a new task called semantic mixing, aiming at blending two different semantics to create a new concept (e.g., corgi + coffee machine — > corgi-alike coffee machine). |
Jun Hao Liew; Hanshu Yan; Daquan Zhou; Jiashi Feng; | arxiv-cs.CV | 2022-10-28 |
| 933 | SynLibras: A Disentangled Deep Generative Model for Brazilian Sign Language Synthesis Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent advances regarding deep generative models have strengthened a realm of approaches in which discriminative and generative tasks are tackled jointly in an … |
Wellington Silveira; Andrew Alaniz; Marina Hurtado; Bernardo Castello Da Silva; Rodrigo Andrade de Bem; | 2022 35th SIBGRAPI Conference on Graphics, Patterns and … | 2022-10-24 |
| 934 | Efficient Hair Style Transfer with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The current state-of-the-art hair synthesis approaches struggle to maintain global composition of the target style and cannot be used in real-time applications due to their high running costs on high-resolution portrait images. Therefore, We propose a novel hairstyle transfer method, called EHGAN, which reduces computational costs to enable real-time processing while improving the transfer of hairstyle with better global structure compared to the other state-of-the-art hair synthesis methods. |
Muhammed Pektas; Baris Gecer; Aybars Ugur; | arxiv-cs.CV | 2022-10-22 |
| 935 | Panoramic Image Style Transfer Technology Based on Multi-attention Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Xin Xiang; Wujian Ye; Yijun Liu; | Proceedings of the 5th International Conference on Computer … | 2022-10-21 |
| 936 | TANGO: Text-driven Photorealistic and Robust 3D Stylization Via Lighting Decomposition IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we focus on stylizing photorealistic appearance renderings of a given surface mesh of arbitrary topology. |
Yongwei Chen; Rui Chen; Jiabao Lei; Yabin Zhang; Kui Jia; | arxiv-cs.CV | 2022-10-20 |
| 937 | K-SALSA: K-Anonymous Synthetic Averaging of Retinal Images Via Local Style Alignment Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: While prior works have explored image de-identification strategies based on synthetic averaging of images in other domains (e.g. facial images), existing techniques face difficulty in preserving both privacy and clinical utility in retinal images, as we demonstrate in our work. We therefore introduce k-SALSA, a generative adversarial network (GAN)-based framework for synthesizing retinal fundus images that summarize a given private dataset while satisfying the privacy notion of k-anonymity. |
Minkyu Jeon; Hyeonjin Park; Hyunwoo J. Kim; Michael Morley; Hyunghoon Cho; | eccv | 2022-10-19 |
| 938 | Learning Visual Styles from Audio-Visual Associations IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present a method for learning visual styles from unlabeled audio-visual data. |
Tingle Li; Yichen Liu; Andrew Owens; Hang Zhao; | eccv | 2022-10-19 |
| 939 | Language-Driven Artistic Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a new task—language-driven artistic style transfer (LDAST)—to manipulate the style of a content image, guided by a text. |
Tsu-Jui Fu; Xin Eric Wang; William Yang Wang; | eccv | 2022-10-19 |
| 940 | CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we aim to devise a universally versatile style transfer method capable of performing artistic, photo-realistic, and video style transfer jointly, without seeing videos during training. |
Zijie Wu; Zhen Zhu; Junping Du; Xiang Bai; | eccv | 2022-10-19 |
| 941 | SCAM! Transferring Humans Between Images with Semantic Cross Attention Modulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details. |
Nicolas Dufour; David Picard; Vicky Kalogeiton; | eccv | 2022-10-19 |
| 942 | WISE: Whitebox Image Stylization By Example-Based Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, adapting or extending these techniques to produce new styles is often a tedious and error-prone task that requires expert knowledge. We propose a new paradigm to alleviate this problem: implementing algorithmic image filtering techniques as differentiable operations that can learn parametrizations aligned to certain reference styles. |
TZSCH WINFRIED L&OUML et. al. | eccv | 2022-10-19 |
| 943 | Cross Attention Based Style Distribution for Controllable Person Image Synthesis IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer. |
XINYUE ZHOU et. al. | eccv | 2022-10-19 |
| 944 | Skeleton-Free Pose Transfer for Stylized 3D Characters IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present the first method that automatically transfers poses between stylized 3D characters without skeletal rigging. |
Zhouyingcheng Liao; Jimei Yang; Jun Saito; Gerard Pons-Moll; Yang Zhou; | eccv | 2022-10-19 |
| 945 | ManiFest: Manifold Deformation for Few-Shot Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We instead propose ManiFest: a framework for few-shot image translation that learns a context-aware representation of a target domain from a few images only. |
Fabio Pizzati; ois Lalonde Jean-Franç Raoul de Charette; | eccv | 2022-10-19 |
| 946 | Vector Quantized Image-to-Image Translation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose introducing the vector quantization technique into the image-to-image translation framework. |
Yu-Jie Chen; Shin-I Cheng; Wei-Chen Chiu; Hung-Yu Tseng; Hsin-Ying Lee; | eccv | 2022-10-19 |
| 947 | Harmonizer: Learning to Perform White-Box Image and Video Harmonization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we observe that adjusting the input arguments of basic image filters, e.g., brightness and contrast, is sufficient for humans to produce realistic images from the composite ones. |
Zhanghan Ke; Chunyi Sun; Lei Zhu; Ke Xu; Rynson W.H. Lau; | eccv | 2022-10-19 |
| 948 | Bi-Level Feature Alignment for Versatile Image Translation and Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper presents a versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence. |
FANGNENG ZHAN et. al. | eccv | 2022-10-19 |
| 949 | Image-Based CLIP-Guided Essence Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Our blending operator combines the powerful StyleGAN generator and the semantic encoder of CLIP in a novel way that is simultaneously additive in both latent spaces, resulting in a mechanism that guarantees both identity preservation and high-level feature transfer without relying on a facial recognition network. |
Hila Chefer; Sagie Benaim; Roni Paiss; Lior Wolf; | eccv | 2022-10-19 |
| 950 | Interpolated SelectionConv for Spherical Images and Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We present a new and general framework for convolutional neural network operations on spherical (or omnidirectional) images. |
David Hart; Michael Whitney; Bryan Morse; | arxiv-cs.CV | 2022-10-18 |
| 951 | Illumination-Aware Style Transfer for Image Harmonization Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image harmonization aims to make composite images visually consistent by adjusting the appearance of the foreground to make it harmonious with the background. Previous methods … |
Teng Ren; Haitao Zhang; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 952 | Revisiting Artistic Style Transfer for Data Augmentation in A Real-Case Scenario Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: A tremendous number of techniques have been proposed to transfer artistic style from one image to another. In particular, techniques exploiting neural representation of data; from … |
Stefano D’Angelo; F. Precioso; F. Gandon; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 953 | Style Transfer Using Optimal Transport Via Wasserstein Distance Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Universal style transfer has been proven to be effective through CNN models and VGG networks. However, how well to apply the algorithm’s style is a separate issue. This problem is … |
Oseok Ryu; Bowon Lee; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 954 | Image Data Augmentation with Unpaired Image-to-Image Camera Model Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Many image datasets are built from web searches, with images taken by various cameras. The variance of camera sources can lead to different camera signals and colors within images … |
Chi Fa Foo; Stefan Winkler; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 955 | Assessment of Image Manipulation Using Natural Language Description: Quantification of Manipulation Direction Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: We propose a novel assessment approach to the performance of image manipulation using natural language descriptions in this paper. Text-guided image manipulation aims to modify an … |
Yuto Watanabe; Ren Togo; Keisuke Maeda; Takahiro Ogawa; M. Haseyama; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 956 | Hyprogan: Breaking The Dimensional Wall From Human to Anime Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image translation from human faces to anime ones brings a low-end, efficient way to create animation characters for animation industry. However, due to the significant … |
Yinpeng Chen; Jiale Zhang; Z. Cao; Hao Lu; Weicai Zhong; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 957 | A Patch-Based Approach for Artistic Style Transfer Via Constrained Multi-Scale Image Matching Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Since a few years and the advent of convolutional neural networks, algorithms for artistic style transfer between images have developed considerably. However, these methods … |
Benjamin Samuth; D. Tschumperlé; J. Rabin; | 2022 IEEE International Conference on Image Processing … | 2022-10-16 |
| 958 | Controllable Style Transfer Via Test-time Training of Implicit Neural Representation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a controllable style transfer framework based on Implicit Neural Representation that pixel-wisely controls the stylized output via test-time training. |
Sunwoo Kim; Youngjo Min; Younghun Jung; Seungryong Kim; | arxiv-cs.CV | 2022-10-14 |
| 959 | Synthetic-to-real Composite Semantic Segmentation in Additive Manufacturing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work demonstrates the possibilities of using physics-based rendering for labeled image dataset generation, as well as image-to-image translation capabilities to improve the accuracy of real image segmentation for AM systems. |
Aliaksei Petsiuk; Harnoor Singh; Himanshu Dadhwal; Joshua M. Pearce; | arxiv-cs.CV | 2022-10-13 |
| 960 | Line Search-Based Feature Transformation for Fast, Stable, and Tunable Content-Style Control in Photorealistic Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a general-purpose transformation that enables controlling the balance between how much content is preserved and the strength of the infused style. |
Tai-Yin Chiu; Danna Gurari; | arxiv-cs.CV | 2022-10-12 |
| 961 | Fine-Grained Image Style Transfer with Visual Transformers IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Such a design usually destroys the spatial information of the input images and fails to transfer fine-grained style patterns into style transfer results. To solve this problem, we propose a novel STyle TRansformer (STTR) network which breaks both content and style images into visual tokens to achieve a fine-grained style transformation. |
Jianbo Wang; Huan Yang; Jianlong Fu; Toshihiko Yamasaki; Baining Guo; | arxiv-cs.CV | 2022-10-11 |
| 962 | Adaptive Affine Transformation: A Simple and Effective Operation for Spatial Misaligned Image Generation IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: One challenging problem, named spatial misaligned image generation, describing a translation between two face/pose images with large spatial deformation, is widely faced in tasks … |
Zhimeng Zhang; Yu-qiong Ding; | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 963 | Bridging CLIP and StyleGAN Through Latent Alignment for Image Editing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we manage to achieve inference-time optimization-free diverse manipulation direction mining by bridging CLIP and StyleGAN through Latent Alignment (CSLA). |
Wanfeng Zheng; Qiang Li; Xiaoyan Guo; Pengfei Wan; Zhongyuan Wang; | arxiv-cs.CV | 2022-10-10 |
| 964 | Photorealistic Style Transfer Via Adaptive Filtering and Channel Seperation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The problem of color and texture distortion remains unsolved in the photorealistic style transfer task. It is mainly caused by the interference between color and texture during … |
HONGWEI DING et. al. | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 965 | Emotional Machines: Toward Affective Virtual Environments Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Emotional Machines is an interactive installation that builds affective virtual environments through spoken language. In response to the existing limitations of emotion … |
Jorge Forero; Gilberto Bernardes; Mónica Mendes; | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 966 | CACOLIT: Cross-domain Adaptive Co-learning for Imbalanced Image-to-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: State-of-the-art unsupervised image-to-image translation (I2I) methods have made great progress on transferring images from a source domain X to a target domain Y. However, … |
Yijun Wang; Tao Liang; Jianxin Lin; | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 967 | D2Animator: Dual Distillation of StyleGAN For High-Resolution Face Animation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: The style-based generator architectures (e.g. StyleGAN v1, v2) largely promote the controllability and explainability of Generative Adversarial Networks (GANs). Many researchers … |
Zhuo Chen; Chaoyue Wang; Haimei Zhao; Bo Yuan; Xiu Li; | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 968 | Text Style Transfer Based on Multi-factor Disentanglement and Mixture Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text style transfer aims to transfer the reference style of one text image to another text image. Previous works have only been able to transfer the style to a binary text image. … |
Anna Zhu; Zhanhui Yin; Brian Kenji Iwana; Xinyu Zhou; Shengwu Xiong; | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 969 | Detach and Attach: Stylized Image Captioning Without Paired Stylized Dataset IF:3 Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Stylized Image Captioning aims to generate captions with accurate image content and stylized elements simultaneously. However, large-scaled image and stylized caption pairs cost … |
YUTONG TAN et. al. | Proceedings of the 30th ACM International Conference on … | 2022-10-10 |
| 970 | Attention-Guided Generative Adversarial Network for Explainable Thermal to Visible Face Recognition Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Thermal to visible face image translation aims at synthesizing high-fidelity visible face images from thermal counterparts, placing emphasis on preserving the identity of the … |
Cunjian Chen; David Anghelone; Philippe Faure; A. Dantcheva; | 2022 IEEE International Joint Conference on Biometrics … | 2022-10-10 |
| 971 | Neuronal Electrical Activity Pattern Extracted By 3D Clustering and Discriminated By A Deep CNN Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Analyzing the dynamics of neural activity patterns using an electrophysiological approach is important for understanding the basis of information processing in a brain. In this … |
Kaito Ogomori; Suguru N. Kudoh; | 2022 IEEE International Conference on Systems, Man, and … | 2022-10-09 |
| 972 | SST-GAN: Single Sample-based Realistic Traffic Image Generation for Parallel Vision Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: To improve their adaptability to various kinds of driving situations, deep learning-based vision algorithms need images from rare scenes, such as extreme weather conditions and … |
Jiangong Wang; Yutong Wang; Yonglin Tian; Xiao Wang; Fei-Yue Wang; | 2022 IEEE 25th International Conference on Intelligent … | 2022-10-08 |
| 973 | A Multi-view Driver Drowsiness Detection Method Using Transfer Learning and Population-based Sampling Strategy Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Driver drowsiness is an important factor in traffic safety. Thus, many researchers endeavor to develop a reliable driver drowsiness detection system. However, the large variation … |
Jinxin Chen; Zhenwu Fang; Jinxiang Wang; Jiansong Chen; Guo-dong Yin; | 2022 IEEE 25th International Conference on Intelligent … | 2022-10-08 |
| 974 | CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for A Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Disentanglement, interpretability, and controllability are also hard to guarantee for manipulation. To alleviate these problems, we propose to define corpus subspaces spanned by relevant prompts to capture specific image characteristics. |
Chenliang Zhou; Fangcheng Zhong; Cengiz Oztireli; | arxiv-cs.CV | 2022-10-08 |
| 975 | MultiStyleGAN: Multiple One-shot Image Stylizations Using A Single GAN Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a MultiStyleGAN method that is capable of producing multiple different stylizations at once by fine-tuning a single generator. |
Viraj Shah; Ayush Sarkar; Sudharsan Krishnakumar Anitha; Svetlana Lazebnik; | arxiv-cs.CV | 2022-10-08 |
| 976 | Pose Guided Human Image Synthesis with Partially Decoupled GAN Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, it is difficult to recover the detailed texture of the whole human image. To alleviate this problem, we propose a method by decoupling the human body into several parts (\eg, hair, face, hands, feet, \etc) and then using each of these parts to guide the synthesis of a realistic image of the person, which preserves the detailed information of the generated images. |
Jianhan Wu; Jianzong Wang; Shijing Si; Xiaoyang Qu; Jing Xiao; | arxiv-cs.CV | 2022-10-07 |
| 977 | FastCLIPstyler: Optimisation-free Text-based Image Style Transfer Using Style Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present FastCLIPstyler, a generalised text-based image style transfer model capable of stylising images in a single forward pass for arbitrary text inputs. |
ANANDA PADHMANABHAN SURESH et. al. | arxiv-cs.CV | 2022-10-07 |
| 978 | LDEdit: Towards Generalized Text Guided Image Manipulation Via Latent Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose an optimization-free method for the task of generic image manipulation from text prompts. |
Paramanand Chandramouli; Kanchana Vaishnavi Gandikota; | arxiv-cs.CV | 2022-10-05 |
| 979 | Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer By Permuting Textures Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose Pose Transfer by Permuting Textures (PT$^2$), an approach for self-driven human pose transfer that disentangles pose from texture at the patch-level. |
Nannan Li; Kevin J. Shih; Bryan A. Plummer; | arxiv-cs.CV | 2022-10-04 |
| 980 | Federated Domain Generalization for Image Recognition Via Cross-Client Style Transfer IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose a novel domain generalization method for image recognition under federated learning through cross-client style transfer (CCST) without exchanging data samples. |
Junming Chen; Meirui Jiang; Qi Dou; Qifeng Chen; | arxiv-cs.CV | 2022-10-03 |
| 981 | Diffusion-based Image Translation Using Disentangled Style and Content Representation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Unfortunately, due to the stochastic nature of diffusion models, it is often difficult to maintain the original content of the image during the reverse diffusion. To address this, here we present a novel diffusion-based unsupervised image translation method using disentangled style and content representation. |
Gihyun Kwon; Jong Chul Ye; | arxiv-cs.CV | 2022-09-30 |
| 982 | PerSign: Personalized Bangladeshi Sign Letters Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Bangladeshi Sign Language (BdSL) – like other sign languages – is tough to learn for general people, especially when it comes to expressing letters. In this poster, we propose PerSign, a system that can reproduce a person’s image by introducing sign gestures in it. |
Mohammad Imrul Jubair; Ali Ahnaf; Tashfiq Nahiyan Khan; Ullash Bhattacharjee; Tanjila Joti; | arxiv-cs.CV | 2022-09-29 |
| 983 | RETRACTED: Garment Image Style Transfer Based on Deep Learning Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Before neural networks, image style transfer procedures had a common idea: analyze images with a certain style, build a mathematical or statistical model for the style, and then … |
Jing Wang; | Journal of Intelligent & Fuzzy Systems | 2022-09-28 |
| 984 | One-side Virtual Histological Staining Model for Complex Human Samples Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Virtual histological staining technique with a label-free auto-fluorescence image as an input is a challenging scientific pursuit to visualize complicated biological structures … |
Lulin Shi; Ivy H. M. Wong; Claudia T. K. Lo; T. T. Wong; | 2022 IEEE-EMBS International Conference on Biomedical and … | 2022-09-27 |
| 985 | An Intelligent Registration Method of Heterogeneous Remote Sensing Images Based on Style Transfer Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Intelligent registration of heterogeneous remote sensing images is a hot issue in the field of remote sensing and has important research and application values. Due to the … |
Haoyang Tang; Xin Miao; Jiakun Shi; Zhifan Hua; Dongfang Yang; | Proceedings of the 2022 5th International Conference on … | 2022-09-23 |
| 986 | Improved GAN Model for Image Animation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Image-to-image translation is a meaningful and challenging task in computer vision and artistic style transfer. It aims to learn a function which can transfer an image with other … |
Sirong Re; Jiaxin Li; Yiran Li; Junan Mao; | 2022 IEEE 5th International Conference on Information … | 2022-09-23 |
| 987 | VToonify: Controllable High-Resolution Portrait Video Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we investigate the challenging controllable high-resolution portrait video style transfer by introducing a novel VToonify framework. |
Shuai Yang; Liming Jiang; Ziwei Liu; Chen Change Loy; | arxiv-cs.CV | 2022-09-22 |
| 988 | StyleTime: Style Transfer for Synthetic Time Series Generation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, a novel formulation of time series style transfer is proposed for the purpose of synthetic data generation and enhancement. |
Yousef El-Laham; Svitlana Vyetrenko; | arxiv-cs.LG | 2022-09-22 |
| 989 | Spoken-Text-Style Transfer with Conditional Variational Autoencoder and Content Word Storage Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Text style transfer is the task of converting textual style while preserving content. Content preservation is still challenging in text style transfer under the training condition … |
Daiki Yoshioka; Yusuke Yasuda; Noriyuki Matsunaga; Yamato Ohtani; T. Toda; | Interspeech | 2022-09-18 |
| 990 | Correlation-based and Content-enhanced Network for Video Style Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save |
Hong-Shang Lin; Mengmeng Wang; Yong Liu; Jiaxin Kou; | Pattern Analysis and Applications | 2022-09-18 |
| 991 | StyleGAN-based CLIP-guided Image Shape Manipulation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: In this paper, we propose a text-guided image manipulation method which focuses on editing shape attribute using text description. We combine an image generation model, StyleGAN2, … |
Yuchen Qian; Kohei Yamamoto; Keiji Yanai; | Proceedings of the 19th International Conference on … | 2022-09-14 |
| 992 | A New Face Image Manipulation Reveal Scheme Based on Face Detection and Image Watermarking Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Face image manipulation (FIM) algorithms and applications are increasing and distributing rapidly. Nowadays, one can easily find an application to manipulate face images for … |
Zahraa Aqeel Salih; R. T. Mohammed; Khamis A. Zidan; B. Khoo; | 2022 IEEE International Conference on Artificial … | 2022-09-13 |
| 993 | High-resolution Semantically-consistent Image-to-image Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work proposes an unsupervised domain adaptation model that preserves semantic consistency and per-pixel quality for the images during the style-transferring phase. |
MIKHAIL SOKOLOV et. al. | arxiv-cs.CV | 2022-09-13 |
| 994 | High-Resolution Semantically Consistent Image-to-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Deep learning has become one of remote sensing scientists’ most efficient computer vision tools in recent years. However, the lack of training labels for the remote sensing … |
MIKHAIL SOKOLOV et. al. | IEEE Journal of Selected Topics in Applied Earth … | 2022-09-13 |
| 995 | Time-of-Day Neural Style Transfer for Architectural Photographs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we specialize a neural style transfer method for architectural photography. |
Yingshu Chen; Tuan-Anh Vu; Ka-Chun Shum; Binh-Son Hua; Sai-Kit Yeung; | arxiv-cs.CV | 2022-09-13 |
| 996 | Lossless Coding of Multimodal Image Pairs Based on Image-To-Image Translation Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Multimodal image coding often uses standard encoding algorithms, which do not exploit multimodality characteristics. This paper proposes a new cross-modality prediction approach … |
Joao O. Parracho; Lucas A. Thomaz; Luís M. N. Tavora; P. Assunção; S. Faria; | 2022 10th European Workshop on Visual Information … | 2022-09-11 |
| 997 | Generalized One-shot Domain Adaptation of Generative Adversarial Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we focus on the one-shot case, which is more challenging and rarely explored in previous works. |
ZICHENG ZHANG et. al. | arxiv-cs.CV | 2022-09-08 |
| 998 | Pose Guided Human Motion Transfer By Exploiting 2D and 3D Information Summary Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Human motion transfer aims to animate the pose of a human in a source image driven by the poses of a human in a target video. To warp (transfer) human poses, most of the existing … |
Yahui Zhang; Shaodi You; Sezer Karaoglu; T. Gevers; | 2022 International Conference on 3D Vision (3DV) | 2022-09-01 |
| 999 | AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose AWADA, an Attention-Weighted Adversarial Domain Adaptation framework for creating a feedback loop between style-transformation and detection task. |
Maximilian Menke; Thomas Wenzel; Andreas Schwung; | arxiv-cs.CV | 2022-08-31 |
| 1000 | Robust Sound-Guided Image Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a novel approach that first extends the image-text joint embedding space with sound and applies a direct latent optimization method to manipulate a given image based on audio input, e.g., the sound of rain. |
SEUNG HYUN LEE et. al. | arxiv-cs.CV | 2022-08-30 |