ICCV

The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models

Laura Niss, Kevin Vogt-Lowell, Theodoros Tsiligkaridis

机构 * MIT Lincoln Laboratory（麻省理工学院林肯实验室） 纠错

Comments Accepted to ICCV 2025

Class-Wise Federated Averaging for Efficient Personalization

Gyuejeong Lee, Daeyoung Choi

机构 * SAKAK Inc.（SAKAK公司） ； The Cyber University of Korea（韩国网络大学） 纠错

Journal ref Published in ICCV 2025

IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation

Wenxuan Guo, Xiuwei Xu, Hang Yin, Ziwei Wang, Jianjiang Feng, Jie Zhou, Jiwen Lu

机构 * Tsinghua University（清华大学） ； Nanyang Technological University（南洋理工大学） 纠错

Comments Accepted to ICCV 2025. Project page: https://gwxuan.github.io/IGL-Nav/

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

Guanning Zeng, Xiang Zhang, Zirui Wang, Haiyang Xu, Zeyuan Chen, Bingnan Li, Zhuowen Tu

机构 * Tsinghua University（清华大学） ； UC San Diego（加州大学圣地亚哥分校） ； UC Berkeley（加州大学伯克利分校） 纠错

Comments ICCV 2025

On-Device Diffusion Transformer Policy for Efficient Robot Manipulation

Yiming Wu, Huan Wang, Zhenghao Chen, Jianxin Pang, Dong Xu

机构 * School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学） ； School of Engineering, Westlake University（工程学院，西湖大学） ； School of Information and Physical Sciences, University of Newcastle（信息与物理科学学院，新castle大学） ； UBTech Robotics Corp.（UBTech机器人公司） 纠错

Comments ICCV 2025

Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints

Jens U. Kreber, Joerg Stueckler

机构 * University of Augsburg（奥格斯堡大学） 纠错

Comments Accepted for publication at the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation

Qi Chen, Lingxiao Yang, Yun Chen, Nailong Zhao, Jianhuang Lai, Jie Shao, Xiaohua Xie

机构 * Sun Yat-sen University（中山大学） ； ByteDance Intelligent Creation（字节跳动智能创作） ； University of Surrey（Surrey大学） ； Alibaba Cloud Computing（阿里巴巴云计算） 纠错

Comments Accepted to ICCV 2025

Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting

Seunggeun Chi, Enna Sachdeva, Pin-Hao Huang, Kwonjoon Lee

机构 * Purdue University West Lafayette（普渡大学西拉法叶分校） ； Honda Research Institute USA（本田美国研究院） 纠错

Comments ICCV 2025 (Highlight)

DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space

Junyu Chen, Dongyun Zou, Wenkun He, Junsong Chen, Enze Xie, Song Han, Han Cai

机构 * NVIDIA 纠错

Comments ICCV 2025

Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents

Janika Deborah Gajo, Gerarld Paul Merales, Jerome Escarcha, Brenden Ashley Molina, Gian Nartea, Emmanuel G. Maminta, Juan Carlos Roldan, Rowel O. Atienza

机构 * EEEI, University of the Philippines（电子工程学院，菲律宾大学） ； AI Graduate Program, University of the Philippines（人工智能研究生项目，菲律宾大学） 纠错

Comments 14 pages, accepted in ICCV 2025 Workshop on RetailVision

Occlusion-robust Stylization for Drawing-based 3D Animation

Sunjae Yoon, Gwanhyeong Koo, Younghwan Lee, Ji Woo Hong, Chang D. Yoo

机构 * School of Electrical Engineering, KAIST（电气工程学院，韩国科学技术院） 纠错

Comments 11 pages, 13 figures, ICCV 2025

Representation Shift: Unifying Token Compression with FlashAttention

Joonmyung Choi, Sanghyeok Lee, Byungoh Ko, Eunseo Kim, Jihyung Kil, Hyunwoo J. Kim

机构 * Korea University（韩国大学） ； Adobe Research（Adobe研究） ； KAIST（韩国科学技术院） 纠错

Comments International Conference on Computer Vision (ICCV), 2025

SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies

Liang Han, Xu Zhang, Haichuan Song, Kanle Shi, Yu-Shen Liu, Zhizhong Han

机构 * School of Software, Tsinghua University（清华大学软件学院） ； Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院） ； China Telecom（中国电信） ； Kuaishou Technology（快手科技） ； Department of Computer Science, Wayne State University（韦恩州立大学计算机科学系） 纠错

Comments Accepted by ICCV 2025

Steering Guidance for Personalized Text-to-Image Diffusion Models

Sunghyun Park, Seokeon Choi, Hyoungwoo Park, Sungrack Yun

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

Comments ICCV 2025

Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence

Danzhen Fu, Jiagao Hu, Daiguo Zhou, Fei Wang, Zepeng Wang, Wenhua Liao

机构 * MiLM Plus, Xiaomi Inc.（小米公司） 纠错

Comments ICCV 2025 Workshop (HiGen)

TITAN-Guide: Taming Inference-Time AligNment for Guided Text-to-Video Diffusion Models

Christian Simon, Masato Ishii, Akio Hayakawa, Zhi Zhong, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji

机构 * Sony Group Corporation（索尼集团公司） ； Sony AI（索尼人工智能） 纠错

Comments Accepted to ICCV 2025

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

Hyundong Jin, Hyung Jin Chang, Eunwoo Kim

机构 * School of Computer Science and Engineering, Chung-Ang University（Chung-Ang 大学计算机科学与工程学院） ； School of Computer Science, University of Birmingham（布拉德福德大学计算机科学学院） 纠错

Comments Accepted to ICCV 2025

Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior

Erin Rainville, Amirhossein Rasoulian, Hassan Rivaz, Yiming Xiao

机构 * Department of Computer Science and Software Engineering, Concordia University, Montréal, Canada（计算机科学与软件工程系，康科迪亚大学） ； NeuroRx Research, Montréal, Canada（NeuroRx研究公司） ； Department of Electrical and Computer Engineering, Concordia University, Montréal, Canada（电气与计算机工程系，康科迪亚大学） 纠错

Comments Accepted to ICCV 2025 Workshop CVAMD

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product

Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Anton van den Hengel, Ehsan Abbasnejad

Comments To appear in ICCV 2025

Robust 3D Object Detection using Probabilistic Point Clouds from Single-Photon LiDARs

Bhavya Goyal, Felipe Gutierrez-Barragan, Wei Lin, Andreas Velten, Yin Li, Mohit Gupta

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校） ； Ubicept 纠错

Comments ICCV 2025

GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration

Li Mi, Manon Bechaz, Zeming Chen, Antoine Bosselut, Devis Tuia

机构 * EPFL（苏黎世联邦理工学院） 纠错

Comments ICCV 2025. Project page at https://limirs.github.io/GeoExplorer/

Punching Bag vs. Punching Person: Motion Transferability in Videos

Raiyaan Abdullah, Jared Claypoole, Michael Cogswell, Ajay Divakaran, Yogesh Rawat

机构 * Center for Research in Computer Vision, University of Central Florida（计算机视觉研究中心，中央佛罗里达大学） ； Center for Vision Technology, SRI International（视觉技术中心，SRI国际） 纠错

Comments Accepted to ICCV 2025 main conference

A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition

Jie Zhu, Yiyang Su, Minchul Kim, Anil Jain, Xiaoming Liu

机构 * Department of Computer Science and Engineering, Michigan State University（计算机科学与工程系，密歇根州立大学） 纠错

Comments Accepted to ICCV 2025. 11 pages, 5 figures

HumanSAM: Classifying Human-centric Forgery Videos in Human Spatial, Appearance, and Motion Anomaly

Chang Liu, Yunfan Ye, Fan Zhang, Qingyang Zhou, Yuchuan Luo, Zhiping Cai

机构 * National University of Defense Technology（国防科技大学） ； Hunan University（湖南大学） 纠错

Comments ICCV 2025. Project page: https://dejian-lc.github.io/humansam/

CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance

Peiqi Chen, Lei Yu, Yi Wan, Yingying Pei, Xinyi Liu, Yongxiang Yao, Yingying Zhang, Lixiang Ru, Liheng Zhong, Jingdong Chen, Ming Yang, Yongjun Zhang

机构 * Wuhan University（武汉大学） ； Ant Group（蚂蚁集团） 纠错

Comments Accepted to ICCV 2025

DONUT: A Decoder-Only Model for Trajectory Prediction

Markus Knoche, Daan de Geus, Bastian Leibe

机构 * RWTH Aachen University（亚琛工业大学） ； Eindhoven University of Technology（埃因霍温理工大学） 纠错

Comments ICCV 2025. Project page at https://vision.rwth-aachen.de/donut

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Dongbin Zhang, Yunfei Liu, Lijian Lin, Ye Zhu, Yang Li, Minghan Qin, Yu Li, Haoqian Wang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） ； International Digital Economy Academy (IDEA)（国际数字经济学院） 纠错

Comments Accepted to ICCV 2025, Project page: https://eastbeanzhang.github.io/GUAVA/

DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing

Aniruddha Bala, Rohit Chowdhury, Rohan Jaiswal, Siddharth Roheda

机构 * Samsung R&D Institute（三星研发研究所） 纠错

Comments Accepted to ICCV 2025

Simultaneous Motion And Noise Estimation with Event Cameras

Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego

机构 * Keio University（庆应大学） ； Woven by Toyota, Inc.（丰田公司） ； Technische Universität Berlin（柏林技术大学） ； Einstein Center Digital Future, Robotics Institute Germany, and Science of Intelligence Excellence Cluster, Germany（数字未来爱因斯坦中心、德国机器人研究所及智能科学卓越中心） 纠错

Comments 13 pages, 13 figures, 6 tables, Project page https://github.com/tub-rip/ESMD

Journal ref IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Towards a Unified Copernicus Foundation Model for Earth Vision

Yi Wang, Zhitong Xiong, Chenying Liu, Adam J. Stewart, Thomas Dujardin, Nikolaos Ioannis Bountos, Angelos Zavras, Franziska Gerken, Ioannis Papoutsis, Laura Leal-Taixé, Xiao Xiang Zhu

机构 * Technical University of Munich（慕尼黑技术大学） ； Munich Center for Machine Learning（慕尼黑机器学习中心） ； National Technical University of Athens & National Observatory of Athens（雅典国家技术大学及雅典国家天文台） ； Harokopio University of Athens（雅典哈罗科波斯大学） ； NVIDIA（NVIDIA公司） 纠错

Comments Accepted to ICCV 2025. 33 pages, 34 figures