ICCV

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

Byungjun Kim, Shunsuke Saito, Giljoo Nam, Tomas Simon, Jason Saragih, Hanbyul Joo, Junxuan Li

Comments ICCV 2025. Project Page: https://bjkim95.github.io/haircup/

EA-ViT: Efficient Adaptation for Elastic Vision Transformer

Chen Zhu, Wangbo Zhao, Huiwen Zhang, Samir Khaki, Yuhao Zhou, Weidong Tang, Shuo Wang, Zhihang Yuan, Yuzhang Shang, Xiaojiang Peng, Kai Wang, Dawei Yang

机构 * National University of Singapore（国立新加坡大学） ； Xidian University（西安电子科技大学） ； University of Toronto（多伦多大学） ； Houmo AI ； UCF ； Shenzhen Technology University（深圳技术大学） 纠错

Comments Published as a conference paper at ICCV 2025

SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning

Lanmiao Liu, Esam Ghaleb, Aslı Özyürek, Zerrin Yumak

机构 * Max Planck Institute for Psycholinguistics（马克斯·普朗克心理学研究所） ； Donders Institute for Brain Cognition and Behaviour（多纳尔斯脑认知与行为研究所） ； Utrecht University（乌得勒支大学） 纠错

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

PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups

Sakuya Ota, Qing Yu, Kent Fujiwara, Satoshi Ikehata, Ikuro Sato

机构 * Institute of Science Tokyo（东京科学研究所） ； LY Corporation（LY公司） ； National Institute of Informatics (NII)（日本信息处理学会） 纠错

Comments Accepted to ICCV 2025, Project page: https://sinc865.github.io/pino/

CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception

Jiaru Zhong, Jiahao Wang, Jiahui Xu, Xiaofan Li, Zaiqing Nie, Haibao Yu

机构 * Institute for AI Industry Research, Tsinghua University（人工智能产业研究所，清华大学） ； The Hong Kong Polytechnic University（香港理工大学） ； The University of Hong Kong（香港大学） ； School of Vehicle and Mobility, Tsinghua University（车辆与移动技术学院，清华大学） ； Baidu Inc.（百度公司） 纠错

Comments Accepted by ICCV 2025 (Highlight)

Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation

Tianyu Zou, Shengwu Xiong, Ruilin Yao, Yi Rong

机构 * School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院） ； Interdisciplinary Artificial Intelligence Research Institute, Wuhan College（武汉学院交叉人工智能研究院） ； Sanya Science and Education Innovation Park, Wuhan University of Technology（武汉理工大学三亚科学教育创新园） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心） 纠错

Comments 8 pages, 7 figures

Journal ref ICCV 2025

MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective

Weitian Wang, Rai Shubham, Cecilia De La Parra, Akash Kumar

机构 * Robert Bosch GmbH（博世公司） ； Ruhr University Bochum（博尔塔尔大学波恩） 纠错

Comments Accepted to ICCV 2025

Learned Image Compression with Hierarchical Progressive Context Modeling

Yuqi Li, Haotian Zhang, Li Li, Dong Liu

机构 * MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition（脑启发智能感知与认知国家重点实验室） ； University of Science and Technology of China（中国科学技术大学） 纠错

Comments 17 pages, ICCV 2025

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

Ying Ba, Tianyu Zhang, Yalong Bai, Wenyi Mo, Tao Liang, Bing Su, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence（中关村人工智能学院） ； Renmin University of China（中国人民大学） ； Beijing Key Laboratory of Research on Large Models and Intelligent Governance（北京大模型与智能治理重点实验室） ； Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（下一代智能搜索与推荐工程研究中心，教育部） ； iN2X 纠错

Comments Accepted to ICCV 2025

UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis

Zixiang Ai, Zhenyu Cui, Yuxin Peng, Jiahuan Zhou

机构 * Wangxuan Institute of Computer Technology, Peking University（计算机技术研究院，北京大学） 纠错

Comments Accepted by ICCV 2025 as a Poster

Flow Stochastic Segmentation Networks

Fabio De Sousa Ribeiro, Omar Todd, Charles Jones, Avinash Kori, Raghav Mehta, Ben Glocker

Comments Accepted at ICCV 2025

Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting

Xingyu Miao, Haoran Duan, Quanhao Qian, Jiuniu Wang, Yang Long, Ling Shao, Deli Zhao, Ran Xu, Gongjie Zhang

机构 * Durham University（杜ham大学） ； DAMO Academy, Alibaba Group（达摩院，阿里集团） ； Tsinghua University（清华大学） ； UCAS-Terminus AI Lab（北航-terminate人工智能实验室） 纠错

Comments ICCV 2025 (Highlight)

Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift

Mohammed Abdul Hafeez Khan, Parth Ganeriwala, Sarah M. Lehman, Siddhartha Bhattacharyya, Amy Alvarez, Natasha Neogi

机构 * Florida Institute of Technology（佛罗里达理工学院） ； NASA Langley Research Center（美国国家航空航天局兰利研究中心） 纠错

Comments Accepted to ICCV 2025, 2COOOL Workshop. Total 14 pages, 5 tables, and 4 figures

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance

Minghao Fu, Guo-Hua Wang, Xiaohao Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang

机构 * School of Artificial Intelligence, Nanjing University（南京大学人工智能学院） ； National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家实验室） ； Alibaba International Digital Commerce Group（阿里巴巴国际数字商业集团） 纠错

Comments Accepted by ICCV 2025. The code is publicly available at https://github.com/AIDC-AI/TeEFusion

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

Aleksandar Jevtić, Christoph Reich, Felix Wimbauer, Oliver Hahn, Christian Rupprecht, Stefan Roth, Daniel Cremers

Comments ICCV 2025. Christoph Reich and Aleksandar Jevtić - both authors contributed equally. Code: https://github.com/tum-vision/scenedino Project page: https://visinf.github.io/scenedino

Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning

Giwon Lee, Wooseong Jeong, Daehee Park, Jaewoo Jeong, Kuk-Jin Yoon

机构 * Visual Intelligence Lab., KAIST, Korea（韩国韩世科技大学视觉智能实验室） ； Intelligent Systems and Learning Lab., DGIST, Korea（韩国全南国立科学技术院智能系统与学习实验室） 纠错

Comments Accepted at ICCV 2025 (Highlight)

Preserve Anything: Controllable Image Synthesis with Object Preservation

Prasen Kumar Sharma, Neeraj Matiyali, Siddharth Srivastava, Gaurav Sharma

Comments Accepted at ICCV 2025 (main conference)

ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis

Onkar Susladkar, Gayatri Deshmukh, Yalcin Tur, Gorkhem Durak, Ulas Bagci

机构 * Northwestern University（西北大学） ； Stanford University（斯坦福大学） 纠错

Comments Accepted in ICCV 2025

SceneMI: Motion In-betweening for Modeling Human-Scene Interactions

Inwoo Hwang, Bing Zhou, Young Min Kim, Jian Wang, Chuan Guo

机构 * ECE, Seoul National University（电子工程系，首尔国立大学） ； Snap Inc（Snap公司） 纠错

Comments Accepted to ICCV 2025. Project page: http://inwoohwang.me/SceneMI

Motion Synthesis with Sparse and Flexible Keyjoint Control

Inwoo Hwang, Jinseok Bae, Donggeun Lim, Young Min Kim

机构 * ECE, Seoul National University（电子工程系，首尔国立大学） 纠错

Comments Accepted to ICCV 2025. Project Page: http://inwoohwang.me/SFControl

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

Tianyu Fu, Tengxuan Liu, Qinghao Han, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang

机构 * Tsinghua University（清华大学） ； Infinigence-AI ； Peking University（北京大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments ICCV 2025

MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

Ruiyuan Gao, Kai Chen, Bo Xiao, Lanqing Hong, Zhenguo Li, Qiang Xu

机构 * CUHK（中文大学） ； HKUST（香港科技大学） ； Huawei Cloud（华为云） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments ICCV 2025 camera-ready version, Project Website: https://flymin.github.io/magicdrive-v2/