Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection
机构 * South China University of Technology（南方科技大学） ； Tencent AI Lab（腾讯人工智能实验室） ； Foshan University（佛山大学）
Comments ICCV 2025
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detection
机构 * Department of Computer Science and Technology, BNRist, IDG/McGovern Institute for Brain Research, THBI, Tsinghua University（清华大学计算机科学与技术系） ； University of Science and Technology Beijing（北京科技大学） ； Huawei Technologies（华为技术有限公司） ； Chinese Institute for Brain Research (CIBR)（中国脑科学研究院）
Comments Accepted by ICCV 2025
CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation
机构 * University of Illinois Chicago（伊利诺伊大学香槟分校） ； University of Central Florida（中央佛罗里达大学） ； Cisco Research（思科研究）
Comments ICCV 2025. Code is available at https://github.com/hatchetProject/CaO2
HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration
机构 * Northwestern Polytechnical University（北华理工大学） ； Wuhan University（武汉大学） ； Chinese Academy of Sciences（中国科学院） ； Peking University（北京大学） ； Chang’an University（长安大学）
Comments Accepted to ICCV 2025
Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation
机构 * Shanghai Jiao Tong University（上海交通大学） ； Massachusetts Institute of Technology（麻省理工学院）
Comments Accepted by ICCV 2025
TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation
机构 * University of Technology Sydney（悉尼技术大学） ； Zhejiang University（浙江大学）
Comments Accepted by ICCV 2025
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
机构 * Department of Artificial Intelligence, Xiamen University（厦门大学人工智能学院） ； College of Information Science and Technology, Jinan University（济南大学信息科学与技术学院） ； Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（教育部多媒体可信感知与高效计算重点实验室，厦门大学）
Comments Accepted by ICCV 2025
Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising
机构 * CIBM Center for Biomedical Imaging（生物医学成像中心） ； Biomedical Imaging Group（生物医学成像组） ； Univ Rennes, Ensai, CNRS, CREST—UMR 9194（里尔大学、Ensai、CNRS、CREST—UMR 9194）
Comments Accepted at IEEE/CVF International Conference on Computer Vision (ICCV) 2025
CAVIS: Context-Aware Video Instance Segmentation
机构 * DGIST
Comments ICCV 2025. Code: https://github.com/Seung-Hun-Lee/CAVIS
Refining Skewed Perceptions in Vision-Language Contrastive Models through Visual Representations
机构 * University of Utah（犹他大学）
Comments 10 pages, 8 figures
Journal ref In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2025
Leveraging Local Patch Alignment to Seam-cutting for Large Parallax Image Stitching
机构 * College of Information Science and Engineering, Henan University of Technology, China（信息科学与工程学院，河南理工大学，中国）
Comments ICCV 2025
EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
机构 * New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences（模式识别新实验室（NLPR），自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）
Comments Accepted at ICCV 2025
MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding
机构 * Department of Computer Science, Chongqing University, China（重庆大学计算机科学系） ； National Elite Institute of Engineering, Chongqing University, China（重庆大学工程精英研究院） ； College of Computer Science and Technology, National University of Deffense Technology, China（国防科技大学计算机科学与技术学院）
Journal ref ICCV 2025
SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning
机构 * The Laboratory of Intelligent Collaborative Computing of UESTC（UESTC智能协同计算实验室） ； Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province（四川省 Ubiquitous Intelligence and Trusted Services 重点实验室） ； Monash University（墨尔本大学） ； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
Comments Accepted to ICCV 2025
Rethinking Layered Graphic Design Generation with a Top-Down Approach
机构 * HKUST（香港科技大学） ； Adobe Research（Adobe研究院） ； Runway
Comments ICCV 2025
Simulating Refractive Distortions and Weather-Induced Artifacts for Resource-Constrained Autonomous Perception
机构 * University of Hawai‘i at Mānoa（夏威夷大学毛伊分校） ； MindForge AI
Comments This paper has been submitted to the ICCV 2025 Workshop on Computer Vision for Developing Countries (CV4DC) for review
PointGAC: Geometric-Aware Codebook for Masked Point Cloud Modeling
机构 * Jiangxi University of Finance and Economics（江西财经大学） ； Shenzhen University（深圳大学） ； University of Technology Sydney（悉尼科技大学） ； Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Comments ICCV 2025
What's Making That Sound Right Now? Video-centric Audio-Visual Localization
机构 * Seoul National University（首尔国立大学）
Comments Published at ICCV 2025. Project page: https://hahyeon610.github.io/Video-centric_Audio_Visual_Localization/
Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis
机构 * Department of ECE, 2 IPAI, 3 INMC, Seoul National University 4 Department of Pathology, College of Medicine, Seoul National University（1 电子工程系，2 IPAI，3 INMC，首尔国立大学 4 病理学系，医学院，首尔国立大学）
Comments Accepted at ICCV 2025
BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting
机构 * School of Data Science, Fudan University（复旦大学数据科学学院）
Comments Accepted at ICCV 2025, Project Page: https://github.com/fudan-zvg/BezierGS
MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
机构 * Sun Yat-sen University（中山大学） ； Department of Frontier Research, Peng Cheng Laboratory（前沿研究部，鹏城实验室）
Journal ref ICCV, 2025
Driving View Synthesis on Free-form Trajectories with Generative Prior
机构 * Fudan University（复旦大学） ； University of Surrey（Surrey大学）
Comments ICCV 2025
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
Comments ICCV 2025; 26 pages, 12 figures, 10 tables; Code at http://github.com/Xiangxu-0103/LiMA
DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
机构 * NVIDIA
Comments ICCV 2025
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
机构 * Beihang University（北京航空航天大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Tianjin University（天津大学） ； CreateAI
Comments Accepted to ICCV 2025. Code available at: https://github.com/IamCreateAI/CycleVAR
GaussRender: Learning 3D Occupancy with Gaussian Rendering
机构 * ValeoAI ； Sorbonne University（索邦大学）
Comments ICCV 2025
DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors
机构 * Xiaohongshu（小红书） ； ShanghaiTech University（上海科技大学） ； Shanghai Jiao Tong University（上海交通大学）
Comments Accepted by ICCV 2025. Project page: https://dynamic-face.github.io/
OminiControl: Minimal and Universal Control for Diffusion Transformer
机构 * National University of Singapore（新加坡国立大学）
Comments Accepted to ICCV 2025
Active Stereo in the Wild through Virtual Pattern Projection
Comments IJCV extended version of ICCV 2023 paper: "Active Stereo Without Pattern Projector"
TeethGenerator: A two-stage framework for paired pre- and post-orthodontic 3D dental data generation
机构 * Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； Beijing Stomatological Hospital, Capital Medical University（首都医科大学北京 stomatological Hospital）
Comments Accepted by ICCV 2025
