ICCV

ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation

Jimyeong Kim, Jungwon Park, Yeji Song, Nojun Kwak, Wonjong Rhee

机构 * Department of Intelligence and Information（智能与信息系） 纠错

Comments Published at ICCV 2025. Project page: https://wlaud1001.github.io/ReFlex/

Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing

Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang

Comments Accepted by ICCV 2025

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

Yuanrui Wang, Cong Han, Yafei Li, Zhipeng Jin, Xiawei Li, SiNan Du, Wen Tao, Yi Yang, Shuanglong Li, Chun Yuan, Liu Lin

机构 * Tsinghua University（清华大学） ； Baidu Inc.（百度公司） 纠错

Comments Accepted by ICCV 2025

Is Visual in-Context Learning for Compositional Medical Tasks within Reach?

Simon Reiß, Zdravko Marinov, Alexander Jaus, Constantin Seibold, M. Saquib Sarfraz, Erik Rodner, Rainer Stiefelhagen

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； Mercedes-Benz Tech Innovation（梅赛德斯-奔驰技术创新） ； University of Applied Sciences Berlin（柏林应用技术大学） 纠错

Comments Accepted to ICCV 2025

DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover

Youzhuo Wang, Jiayi Ye, Chuyang Xiao, Yiming Zhong, Heng Tao, Hang Yu, Yumeng Liu, Jingyi Yu, Yuexin Ma

机构 * ShanghaiTech University（上海科技大学） ； The University of Hong Kong（香港大学） 纠错

Comments Comments: Accepted by ICCV 2025. Project page: https://dexh2r.github.io/

LUSD: Localized Update Score Distillation for Text-Guided Image Editing

Worameth Chinchuthakun, Tossaporn Saengja, Nontawat Tritrong, Pitchaporn Rewatbowornwong, Pramook Khungurn, Supasorn Suwajanakorn

Comments ICCV 2025. Project page: https://github.com/sincostanx/LUSD

2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos

Marvin Heidinger, Snehal Jauhri, Vignesh Prasad, Georgia Chalvatzaki

机构 * Computer Science Department, Technische Universität Darmstadt（德意志联邦共和国达姆施塔特技术大学计算机科学系） 纠错

Comments ICCV 2025

Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling

Fengxiang Wang, Hongzhen Wang, Di Wang, Zonghao Guo, Zhenyu Zhong, Long Lan, Wenjing Yang, Jing Zhang

机构 * College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学） ； Tsinghua University（清华大学） ； School of Computer Science, Wuhan University（计算机科学学院，武汉大学） ； Zhongguancun Academy（中关村学院） ； Nankai University（南开大学） 纠错

Comments ICCV 2025

Dataset Distillation via the Wasserstein Metric

Haoyang Liu, Yijiang Li, Tiancheng Xing, Peiran Wang, Vibhu Dalal, Luwei Li, Jingrui He, Haohan Wang

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of California, San Diego（加州大学圣地亚哥分校） ； National University of Singapore（新加坡国立大学） ； University of California, Los Angeles（加州大学洛杉矶分校） ； Sri Aurobindo International Centre of Education（斯里阿罗bindo国际教育中心） 纠错

Comments Accepted to ICCV 2025. Project page at https://liu-hy.github.io/WMDD/ and code is available at https://github.com/Liu-Hy/WMDD

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers

Yating Wang, Haoyi Zhu, Mingyu Liu, Jiange Yang, Hao-Shu Fang, Tong He

机构 * Shanghai AI Lab（上海人工智能实验室） ； Tongji（同济） ； USTC（中国科学技术大学） ； ZJU（浙江大学） ； NJU（南京大学） ； SJTU（上海交通大学） 纠错

Comments Accepted by ICCV 2025

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

Zifu Wan, Ce Zhang, Silong Yong, Martin Q. Ma, Simon Stepputtis, Louis-Philippe Morency, Deva Ramanan, Katia Sycara, Yaqi Xie

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted by ICCV 2025. Project page: https://zifuwan.github.io/ONLY/

LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment

Juelin Zhu, Shuaibang Peng, Long Wang, Hanlin Tan, Yu Liu, Maojun Zhang, Shen Yan

机构 * National University of Defense Technology（国防科技大学） ； Westlake University（西湖大学） 纠错

Comments Accepted by ICCV 2025

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions

Siyuan Yao, Rui Zhu, Ziqi Wang, Wenqi Ren, Yanyang Yan, Xiaochun Cao

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Sun Yat-sen University（中山大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； MoE Key Laboratory of Information Technology（教育部信息科学技术重点实验室） ； Guangdong Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室） 纠错

Comments Accepted to ICCV 2025

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang, Yuhang Zheng, Yinfeng Gao, Pengfei Li, Teng Zhang, Zhongpu Xia, Peng Jia, Dongbin Zhao

机构 * CASIA（中国科学院自动化研究所） ； Li Auto（力汽车） ； PCL（鹏城实验室） ； NUS（新加坡国立大学） ； Tsinghua（清华大学） 纠错

Comments ICCV 2025, first version

Context-Aware Academic Emotion Dataset and Benchmark

Luming Zhao, Jingwen Xuan, Jiamin Lou, Yonghui Yu, Wenwu Yang

机构 * Zhejiang Gongshang University（浙江工商大学） ； Zhejiang Yuexiu University（浙江越秀大学） 纠错

Comments Accepted to ICCV 2025

ARIG: Autoregressive Interactive Head Generation for Real-time Conversations

Ying Guo, Xi Liu, Cheng Zhen, Pengfei Yan, Xiaoming Wei

机构 * Vision AI Department, Meituan（美团视觉人工智能部门） 纠错

Comments ICCV 2025. Homepage: https://jinyugy21.github.io/ARIG/

DiGA3D: Coarse-to-Fine Diffusional Propagation of Geometry and Appearance for Versatile 3D Inpainting

Jingyi Pan, Dan Xu, Qiong Luo

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） 纠错

Comments ICCV 2025, Project page: https://rorisis.github.io/DiGA3D/

Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning

Wenjin Mo, Zhiyuan Li, Minghong Fang, Mingwei Fang

机构 * Yale University（耶鲁大学） ； University of Louisville（路易斯维尔大学） ； Guangdong Polytechnic Normal University（广东 polytechnic 正规大学） 纠错

Comments To appear in ICCV 2025

Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes

Chuyan Zhang, Kefan Wang, Yun Gu

机构 * School of Automation and Intelligent Sensing, Institute of Medical Robotics, Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University（自动化与智能感知学院、医疗机器人研究院、图像处理与模式识别研究院、上海交通大学） 纠错

Comments Accepted by ICCV 2025

OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration

Yiming Zuo, Willow Yang, Zeyu Ma, Jia Deng

机构 * Department of Computer Science, Princeton University（计算机科学系，普林斯顿大学） 纠错

Comments Accepted to ICCV 2025. Added additional results and ablations

From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning

Pengkun Jiao, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

机构 * Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理关键实验室，复旦大学计算机学院） ； Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心） ； Singapore Management University（新加坡管理大学） 纠错

Comments ICCV 2025

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Tianming Liang, Kun-Yu Lin, Chaolei Tan, Jianguo Zhang, Wei-Shi Zheng, Jian-Fang Hu

机构 * Sun Yat-sen University（中山大学） ； Southern University of Science and Technology（南方科技大学） 纠错

Comments Accepted to ICCV 2025. Project page: \url{https://isee-laboratory.github.io/ReferDINO}

HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity

Yida Wang, Xueyang Zhang, Kun Zhan, Peng Jia, Xianpeng Lang

机构 * Li Auto Inc.（利自动公司） 纠错

Comments Published in International Conference on Computer Vision (ICCV) 2025

Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model

Shiming Chen, Bowen Duan, Salman Khan, Fahad Shahbaz Khan

机构 * Mohamed bin Zayed University of AI（莫扎伊德大学人工智能学院） ； Huazhong University of Science and Technology（华中科技大学） ； Australian National University（澳大利亚国立大学） ； Linköping University（林雪平大学） 纠错

Comments Accepted to ICCV'25

Visual Textualization for Image Prompted Object Detection

Yongjian Wu, Yang Zhou, Jiya Saiyin, Bingzheng Wei, Yan Xu

机构 * School of Biological Science and Medical Engineering, Beihang University（北京航空航天大学生物科学与医学工程学院） ； ByteDance Inc.（字节跳动公司） 纠错

Comments Accepted by ICCV 2025

Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation

Patrick Glandorf, Bodo Rosenhahn

Comments ICCV'25 Workshops

TurboVSR: Fantastic Video Upscalers and Where to Find Them

Zhongdao Wang, Guodongfang Zhao, Jingjing Ren, Bailan Feng, Shifeng Zhang, Wenbo Li

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室） ； HKUST (Guangzhou)（香港科技大学（广州）） 纠错

Comments ICCV, 2025

Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention

Weida Wang, Changyong He, Jin Zeng, Di Qiu

机构 * School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院） 纠错

Comments This paper has been accepted for publication at the International Conference on Computer Vision (ICCV) 2025

PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions

Mahesh Bhosale, Abdul Wasi, Yuanhao Zhai, Yunjie Tian, Samuel Border, Nan Xi, Pinaki Sarder, Junsong Yuan, David Doermann, Xuan Gong

机构 * University at Buffalo（布法罗大学） ； University of Florida（佛罗里达大学） ； Harvard Medical School（哈佛医学院） 纠错

Comments Accepted to ICCV 2025

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields

Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Masato Taki, Yutaka Matsuo

机构 * Rikkyo University（立命馆大学） ； University of Tokyo（东京大学） ； ATR（ATR研究所） ； Institute of Science Tokyo（东京科学研究院） ； National Institute of Informatics（国家信息研究所） ； NII LLMC（日本信息处理学会LLMC） ； Sony Semiconductor Solutions（索尼半导体解决方案） 纠错

Comments Accepted by ICCV 2025