O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
Comments Accepted at ICCV 2025. Code: https://github.com/Maria-SanVil/O-MaMa Project page: https://maria-sanvil.github.io/O-MaMa/
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection
机构 * CNES（法国国家太空研究中心） ； European Space Agency（欧洲航天局） ； Φ \Phi -Lab（Φ实验室）
Comments Published as a conference paper at ICCV 2025
GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion
机构 * University of Zagreb Faculty of Electrical Engineering and Computing（Zagreb大学电子工程与计算学院）
Comments ICCV 2025
Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts
机构 * Qualcomm AI Research（高通人工智能研究）
Comments Accepted at ICCV 2025
PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representation
机构 * University of Freiburg（弗赖堡大学） ； Fraunhofer IPM（弗劳恩霍夫IPM研究所）
Comments Accepted for the ICCV 2025 e2e3D Workshop. To be published in the Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Predictive Quality Assessment for Mobile Secure Graphics
机构 * Scantrust / University of Amsterdam（Scantrust / 阿姆斯特丹大学）
Comments 8 pages, to appear at ICCV 2025 MIPI Workshop (IEEE)
PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Prediction
机构 * University of Warwick, UK（沃里克大学）
Comments Accepted at ICCV 2025. Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Xiong’an Aerospace Information Research Institute（雄安航空航天信息研究所） ； State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（信息处理国家重点实验室，北京大学计算机学院） ； National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（视觉技术国家工程研究中心，北京大学计算机学院）
Comments Accepted by ICCV 2025
From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition
机构 * National Yang Ming Chiao Tung University（阳明交通大学） ； Google DeepMind（谷歌DeepMind） ； National Taiwan University（国立台湾大学） ； UC Merced（加州大学梅尔塞德斯分校）
Comments ICCV 2025
Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding
机构 * Xidian University（西安电子科技大学） ； KTH Royal Institute of Technology（皇家理工学院） ； Donghai Laboratory（东海实验室）
Comments Accepted by ICCV 2025
Adversarial Robustness of Discriminative Self-Supervised Learning in Vision
机构 * Department of Computer Engineering, Koç University（计算机工程系，科克大学）
Comments ICCV 2025
RG-Attn: Radian Glue Attention for Multi-modality Multi-agent Cooperative Perception
机构 * Sony (China) Limited（索尼（中国）有限公司） ； Renmin University of China（中国人民大学）
Comments Accepted by ICCV 2025 DriveX workshop (Final Version)
Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
机构 * Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克信息研究所，萨尔兰州信息校园） ； ETH Zurich（苏黎世联邦理工学院） ； University of Oxford（牛津大学） ； Saarbrücken Research Center for Visual Computing, Interaction and AI（萨尔布吕肯视觉计算、交互与人工智能研究中心） ； University of Freiburg（弗赖堡大学）
Comments ICCV 2025. Project page: https://genintel.github.io/DIY-SC
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images
机构 * Stanford University（斯坦福大学） ； Google DeepMind（谷歌DeepMind）
Comments ICCV 2025, Project page: https://boyangdeng.com/visual-chronicles , second and third listed authors have equal contributions
MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation
机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments 11 pages, 3 figures, Accepted at ICCV 2025 Workshop CVAMD
AI-Derived Structural Building Intelligence for Urban Resilience: An Application in Saint Vincent and the Grenadines
机构 * The World Bank Group（世界银行集团）
Comments Accepted at the 2nd Workshop on Computer Vision for Developing Countries (CV4DC) at ICCV 2025
EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device
机构 * Georgia Tech（佐治亚理工学院） ； Toyota Research Institute（丰田研究院）
Comments 16 pages, 18 figures, paper accepted at ICCV, 2025
DATA: Domain-And-Time Alignment for High-Quality Feature Fusion in Collaborative Perception
机构 * Southeast University（东南大学） ； Washington State University（华盛顿州立大学）
Comments ICCV 2025, accepted as poster. 22 pages including supplementary materials
RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion
机构 * Seoul National University（首尔国立大学） ； Hanyang University（翰阳大学） ； Hyundai Motor Company（现代汽车公司）
Comments Accepted at ICCV 2025
MAESTRO: Task-Relevant Optimization via Adaptive Feature Enhancement and Suppression for Multi-task 3D Perception
机构 * Hanyang University（翰阳大学） ； Seoul National University（首尔国立大学）
Comments Accepted to ICCV 2025
UIPro: Unleashing Superior Interaction Capability For GUI Agents
机构 * University of Chinese Academy of Sciences (UCAS)（中国科学院大学） ； New Laboratory of Pattern Recognition (NLPR), CASIA（中国科学院自动化所模式识别新实验室） ； State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA（中国科学院多模态人工智能系统国家重点实验室） ； Hong Kong Institute of Science & Innovation, CASIA（中国科学院香港创新科学研究院） ； PolyU ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Comments Accepted to ICCV 2025
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
机构 * Australian Institute for Machine Learning, University of Adelaide, Australia（澳大利亚机器学习研究所，阿德莱德大学，澳大利亚） ； Deakin University, Australia（德肯大学，澳大利亚） ； Flinders University, Australia（弗林德斯大学，澳大利亚）
Comments Accepted at IEEE/CVF International Conference on Computer Vision (ICCV), 2025
DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance
机构 * National Yang Ming Chiao Tung University（国家阳明交通大学） ； MediaTek Inc.（联发科技）
Comments Accepted by ICCV 2025
Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
Comments ICCV 2025
Sparse Multiview Open-Vocabulary 3D Detection
机构 * Centre for Mathematical Sciences, Lund University（数学科学中心，卢德大学） ； Sony Corporation, Lund Laboratory, Sweden（索尼公司，卢德实验室，瑞典）
Comments ICCV 2025; OpenSUN3D Workshop; Camera ready version
Global Regulation and Excitation via Attention Tuning for Stereo Matching
机构 * City University of Hong Kong（香港城市大学） ； Hon Hai Research Institute（富士康研究院）
Comments International Conference on Computer Vision (ICCV 2025)
Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data
机构 * Independent Researcher（独立研究者）
Comments Accepted to Curated Data for Efficient Learning Workshop at ICCV 2025
Enriched Feature Representation and Motion Prediction Module for MOSEv2 Track of 7th LSVOS Challenge: 3rd Place Solution
机构 * Computer Vision Lab., Department of Computer Science, Hanyang University（计算机视觉实验室，计算机科学系，翰林大学）
Comments 5 pages,2 figures, ICCV Workshop (MOSEv2 Track of 7th LSVOS Challenge)
SmolRGPT: Efficient Spatial Reasoning for Warehouse Environments with 600M Parameters
机构 * Embia, Computer Science Department, Faculty of Science, Université de Moncton（Embia计算机科学系，科学学院，蒙特龙大学）
Comments 9 pages, 3 figures, IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
机构 * MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences（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 by ICCV 2025
