PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
机构 * Dept. of CSE, Korea University（计算机科学与工程系，韩国大学）
Comments Accepted to ICCV 2025. https://mks0601.github.io/PERSONA/
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Stable Diffusion Models are Secretly Good at Visual In-Context Learning
机构 * Apple（苹果公司） ； University of Maryland - College Park（马里兰大学-College Park）
Comments Accepted to ICCV 2025
Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?
机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； Luleå University of Technology（吕勒奥技术大学） ； National Technical University of Athens（雅典国家技术大学） ； University of West Attica（西阿提卡大学）
Comments Accepted at ICCV Workshop VisionDocs
COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets
机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics（人工智能学院，南京航空航天大学） ； ByteDance Inc.（字节跳动公司） ； Tsinghua University（清华大学） ； Shanghai Jiaotong University（上海交通大学）
Comments ICCV 2025
RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
机构 * vLAR Group, The Hong Kong Polytechnic University（vLAR组，香港理工大学）
Comments ICCV 2025 Highlight. Shenxing and Jinxi are co-first authors. Code and data are available at: https://github.com/vLAR-group/RayletDF
TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos
机构 * vLAR Group, The Hong Kong Polytechnic University（vLAR小组，香港理工大学）
Comments ICCV 2025. Code and data are available at: https://github.com/vLAR-group/TRACE
NegFaceDiff: The Power of Negative Context in Identity-Conditioned Diffusion for Synthetic Face Generation
机构 * Fraunhofer IGD（弗劳恩霍夫研究所） ； TU Darmstadt（图宾根大学）
Comments Accepted at ICCV Workshops
BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment
机构 * The Chinese University of Hong Kong（香港中文大学） ； University at Buffalo（布法罗大学） ； Spatial AI & Robotics Lab（空间人工智能与机器人实验室）
Comments ICCV 2025 Highlight
Journal ref IEEE/CVF International Conference on Computer Vision (ICCV), 2025
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
机构 * Huazhong University of Science and Technology（华中科技大学） ； MEGVII Technology（梅格维七科技） ； Mach Drive（马奇驱动） ； The University of Hong Kong（香港大学）
Comments Accepted by ICCV 2025. The code is available at https://github.com/LMD0311/HERMES
GenAI Confessions: Black-box Membership Inference for Generative Image Models
机构 * Stanford University（斯坦福大学） ； University of California, Berkeley（加州大学伯克利分校）
Comments https://genai-confessions.github.io
Journal ref ICCV-W 2025
Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
机构 * ISIR, Sorbonne Université（ISIR，索邦大学）
Comments ICCV 2025. The first three authors contributed equally. Project page and code: https://pegah- kh.github.io/projects/lmm-finetuning-analysis-and-steering/
Pretrained Reversible Generation as Unsupervised Visual Representation Learning
机构 * Xi’an Jiaotong University（西安交通大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； SenseTime（商汤科技） ； The Chinese University of Hong Kong（香港中文大学） ； Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Comments Accepted by ICCV 2025
RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata
机构 * Issaquah High School（伊萨夸高中） ； University of Washington（华盛顿大学）
Comments Accepted to the ICCV'25 Workshop on Vision Foundation Models and Generative AI for Accessibility: Challenges and Opportunities
A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition
机构 * University of Waterloo（滑铁卢大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Comments Accepted for the IEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, Hawaii, USA. 1st MSLR Workshop 2025
FusionEnsemble-Net: An Attention-Based Ensemble of Spatiotemporal Networks for Multimodal Sign Language Recognition
机构 * University of Waterloo（滑铁卢大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Comments Accepted for the IEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, Hawaii, USA. 1st MSLR Workshop 2025
Harnessing Input-Adaptive Inference for Efficient VLN
机构 * Oregon State University（俄勒冈州立大学）
Comments Accepted to ICCV 2025 [Poster]
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
机构 * Sun Yat-Sen University（中山大学） ； Peng Cheng Laboratory（鹏城实验室） ； Nanyang Technological University（南洋理工大学） ； National University of Singapore（新加坡国立大学） ； National Key Laboratory of Science and Technology on Information System Security（国家信息系统安全科学技术重点实验室） ； Nsfocus
Comments Accepted by ICCV 2025
