ICCV

ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning

Jongseo Lee, Kyungho Bae, Kyle Min, Gyeong-Moon Park, Jinwoo Choi

机构 * Kyung Hee University（Kyung Hee 大学） ； Danggeun Market Inc.（Danggeun Market 公司） ； Intel Labs（Intel 实验室） ； Korea University（韩国大学） 纠错

Comments 2025 ICCV Highlight paper, 17 pages including supplementary material

UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving

Yuping Wang, Xiangyu Huang, Xiaokang Sun, Mingxuan Yan, Shuo Xing, Zhengzhong Tu, Jiachen Li

Comments IEEE/CVF International Conference on Computer Vision (ICCV 2025); Project website: https://uniocc.github.io/

Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction

Luyao Tang, Kunze Huang, Chaoqi Chen, Yuxuan Yuan, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学） ； School of Informatics, Xiamen University（厦门大学信息学院） ； Shenzhen University（深圳大学） ； The Chinese University of Hong Kong（香港中文大学） ； The University of Hong Kong（香港大学） 纠错

Comments Accepted by ICCV 2025 as *** Highlight ***!

EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba

Quang Nguyen, Nhat Le, Baoru Huang, Minh Nhat Vu, Chengcheng Tang, Van Nguyen, Ngan Le, Thieu Vo, Anh Nguyen

机构 * FPT Software AI Center（FPT软件AI中心） ； The University of Western Australia（西澳大学） ； TU Wien（维也纳技术大学） ； Meta ； University of Arkansas（阿肯色大学） ； National University of Singapore（新加坡国立大学） ； University of Liverpool（利物浦大学） 纠错

Comments Accepted at The 2025 IEEE/CVF International Conference on Computer Vision (ICCV 2025)

On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations

Amir Mehrpanah, Matteo Gamba, Kevin Smith, Hossein Azizpour

机构 * KTH Royal Institute of Technology（皇家理工学院） 纠错

Comments 23 pages, 14 figures, to be published in International Conference on Computer Vision 2025

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

Yuhao Sun, Yihua Zhang, Gaowen Liu, Hongtao Xie, Sijia Liu

机构 * University of Science and Technology of China（中国科学技术大学） ； Institute of Artificial Intelligence（人工智能研究院） ； Hefei Comprehensive National Science Center（合肥综合国家科学中心） ； Michigan State University（密歇根州立大学） ； Cisco Research（思科研究） 纠错

Comments Accepted by ICCV 2025

iSafetyBench: A video-language benchmark for safety in industrial environment

Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas

机构 * University of Central Florida（中央佛罗里达大学） 纠错

Comments Accepted to VISION'25 - ICCV 2025 workshop

Class-Proportional Coreset Selection for Difficulty-Separable Data

Elisa Tsai, Haizhong Zheng, Atul Prakash

机构 * University of Michigan（密歇根大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments This paper has been accepted to the ICCV 2025 Workshop on Curated Data for Efficient Learning (CDEL)

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

Runjia Li, Philip Torr, Andrea Vedaldi, Tomas Jakab

机构 * University of Oxford（牛津大学） 纠错

Comments ICCV 2025 highlight. Project page: https://v-mem.github.io

CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

Lei Tian, Xiaomin Li, Liqian Ma, Hao Yin, Zirui Zheng, Hefei Huang, Taiqing Li, Huchuan Lu, Xu Jia

机构 * Dalian University of Technology（大连理工大学） ； ZMO AI Inc.（ZMO人工智能公司） 纠错

Comments ICCV 2025

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting

Atin Pothiraj, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校） 纠错

Comments ICCV 2025

OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM

Jinhong Wang, Shuo Tong, Jian liu, Dongqi Tang, Weiqiang Wang, Wentong Li, Hongxia Xu, Danny Chen, Jintai Chen, Jian Wu

机构 * College of Computer Science & Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； Transvascular Implantation Devices Research Institute and Liangzhu Laboratory（血管植入物研究机构和良渚实验室） ； Ant Group（蚂蚁集团） ； University of Notre Dame（圣母大学） ； HKUST (Guangzhou)（香港科技大学（广州）） 纠错

Comments Accepted by ICCV 2025

TikZero: Zero-Shot Text-Guided Graphics Program Synthesis

Jonas Belouadi, Eddy Ilg, Margret Keuper, Hideki Tanaka, Masao Utiyama, Raj Dabre, Steffen Eger, Simone Paolo Ponzetto

Comments Accepted at ICCV 2025 (highlight); Project page: https://github.com/potamides/DeTikZify

NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning

Zhixi Cai, Fucai Ke, Simindokht Jahangard, Maria Garcia de la Banda, Reza Haffari, Peter J. Stuckey, Hamid Rezatofighi

机构 * Monash University（莫纳什大学） 纠错

Comments ICCV 2025

Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation

Yuxuan Wang, Xuanyu Yi, Haohan Weng, Qingshan Xu, Xiaokang Wei, Xianghui Yang, Chunchao Guo, Long Chen, Hanwang Zhang

机构 * Nanyang Technological University（南洋理工大学） ； Tencent Hunyuan（腾讯 Hunyuan） ； South China University of Technology（华南理工大学） ； The Hong Kong Polytechnic University（香港理工大学） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

Comments accepted to ICCV 2025

Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness

Qifan Yu, Zhebei Shen, Zhongqi Yue, Yang Wu, Bosheng Qin, Wenqiao Zhang, Yunfei Li, Juncheng Li, Siliang Tang, Yueting Zhuang

机构 * Zhejiang University（浙江大学） ； Nanyang Technological University（南洋理工大学） ； Ant Group（蚂蚁集团） 纠错

Comments ICCV 2025 Highlight

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

Junho Kim, Hyungjin Chung, Byung-Hoon Kim

机构 * EverEx ； Yonsei University（延世大学） 纠错

Comments ICCV 2025

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image

Geonhee Sim, Gyeongsik Moon

机构 * Dept. of CSE, Korea University（计算机科学与工程系，韩国大学） 纠错

Comments Accepted to ICCV 2025. https://mks0601.github.io/PERSONA/

Stable Diffusion Models are Secretly Good at Visual In-Context Learning

Trevine Oorloff, Vishwanath Sindagi, Wele Gedara Chaminda Bandara, Ali Shafahi, Amin Ghiasi, Charan Prakash, Reza Ardekani

机构 * Apple（苹果公司） ； University of Maryland - College Park（马里兰大学-College Park） 纠错

Comments Accepted to ICCV 2025

Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?

Vittorio Pippi, Konstantina Nikolaidou, Silvia Cascianelli, George Retsinas, Giorgos Sfikas, Rita Cucchiara, Marcus Liwicki

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） 纠错

Comments Accepted at ICCV Workshop VisionDocs

COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

Lingyu Chen, Yawen Zeng, Yue Wang, Peng Wan, Guo-chen Ning, Hongen Liao, Daoqiang Zhang, Fang Chen

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） 纠错

Comments ICCV 2025

RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians

Shenxing Wei, Jinxi Li, Yafei Yang, Siyuan Zhou, Bo Yang

机构 * vLAR Group, The Hong Kong Polytechnic University（vLAR组，香港理工大学） 纠错

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

Jinxi Li, Ziyang Song, Bo Yang

机构 * vLAR Group, The Hong Kong Polytechnic University（vLAR小组，香港理工大学） 纠错

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

Eduarda Caldeira, Naser Damer, Fadi Boutros

机构 * Fraunhofer IGD（弗劳恩霍夫研究所） ； TU Darmstadt（图宾根大学） 纠错

Comments Accepted at ICCV Workshops

BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

Tongfan Guan, Jiaxin Guo, Chen Wang, Yun-Hui Liu

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） 纠错

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

Xin Zhou, Dingkang Liang, Sifan Tu, Xiwu Chen, Yikang Ding, Dingyuan Zhang, Feiyang Tan, Hengshuang Zhao, Xiang Bai

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） 纠错

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

Matyas Bohacek, Hany Farid

机构 * Stanford University（斯坦福大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

Comments https://genai-confessions.github.io

Journal ref ICCV-W 2025

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering

Pegah Khayatan, Mustafa Shukor, Jayneel Parekh, Arnaud Dapogny, Matthieu Cord

机构 * ISIR, Sorbonne Université（ISIR，索邦大学） 纠错

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

Rongkun Xue, Jinouwen Zhang, Yazhe Niu, Dazhong Shen, Bingqi Ma, Yu Liu, Jing Yang

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） 纠错

Comments Accepted by ICCV 2025

RampNet: A Two-Stage Pipeline for Bootstrapping Curb Ramp Detection in Streetscape Images from Open Government Metadata

John S. O'Meara, Jared Hwang, Zeyu Wang, Michael Saugstad, Jon E. Froehlich

机构 * Issaquah High School（伊萨夸高中） ； University of Washington（华盛顿大学） 纠错

Comments Accepted to the ICCV'25 Workshop on Vision Foundation Models and Generative AI for Accessibility: Challenges and Opportunities