ICCV - arXivDaily 期刊&会议

2507.18569 2025-07-25 cs.CV

Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis

Yanzuo Lu, Yuxi Ren, Xin Xia, Shanchuan Lin, Xing Wang, Xuefeng Xiao, Andy J. Ma, Xiaohua Xie, Jian-Huang Lai

机构 * Sun Yat-Sen University（中山大学）； ByteDance Seed Vision（字节跳动种子视觉）； Guangdong Provincial Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）； Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（教育部机器智能与高级计算重点实验室）； Pazhou Lab (HuangPu), Guangzhou, China（琶洲实验室（黄埔），广州，中国）

Comments Accepted by ICCV 2025 (Highlight)

2410.08989 2025-07-25 cs.LG cs.AI

Zeroth-Order Fine-Tuning of LLMs in Random Subspaces

Ziming Yu, Pan Zhou, Sike Wang, Jia Li, Mi Tian, Hua Huang

机构 * Beijing Normal University（北京师范大学）； Singapore Management University（新加坡国立大学）； TAL Education Group（TAL教育集团）； Engineering Research Center of Intelligent Technology and Educational Application (MOE)（智能技术与教育应用工程研究中心（教育部））

Comments ICCV 2025 camera-ready version

2507.18300 2025-07-25 cs.CV

LMM-Det: Make Large Multimodal Models Excel in Object Detection

Jincheng Li, Chunyu Xie, Ji Ao, Dawei Leng, Yuhui Yin

机构 * AI Research（360人工智能研究院）

Comments Accepted at ICCV 2025

2507.18276 2025-07-25 cs.RO cs.CV

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding

Xiaojie Zhang, Yuanfei Wang, Ruihai Wu, Kunqi Xu, Yu Li, Liuyu Xiang, Hao Dong, Zhaofeng He

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； School of Computer Science, Peking University（北京大学计算机学院）； School of EECS, Peking University（北京大学电子工程学院）

Comments ICCV 2025

2507.18255 2025-07-25 cs.CV

LONG3R: Long Sequence Streaming 3D Reconstruction

Zhuoguang Chen, Minghui Qin, Tianyuan Yuan, Zhe Liu, Hang Zhao

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； IIIS, Tsinghua University（清华大学智能技术学部）； Shanghai Qi Zhi Institute（上海启智研究院）

Comments Accepted by ICCV 2025. Project page: https://zgchen33.github.io/LONG3R/

2507.18173 2025-07-25 cs.CV cs.MM

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

Haodong Zhu, Wenhao Dong, Linlin Yang, Hong Li, Yuguang Yang, Yangyang Ren, Qingcheng Zhu, Zichao Feng, Changbai Li, Shaohui Lin, Runqi Wang, Xiaoyan Luo, Baochang Zhang

机构 * Beihang University（北京航空航天大学）； Communication University of China（中国传媒大学）； Beijing Jiaotong University（北京交通大学）； East China Normal University（华东师范大学）

Journal ref ICCV, 2025

2507.18155 2025-07-25 cs.GR cs.CV cs.LG

GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar

SeungJun Moon, Hah Min Lew, Seungeun Lee, Ji-Su Kang, Gyeong-Moon Park

机构 * Klleon AI Research（Klleon AI研究院）； Korea University（韩国大学）

Comments ICCV 2025, Project page: https://hahminlew.github.io/geoavatar/

2507.15504 2025-07-25 cs.CV

Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization

Bingqing Zhang, Zhuo Cao, Heming Du, Yang Li, Xue Li, Jiajun Liu, Sen Wang

机构 * The University of Queensland, Australia（昆士兰大学）； CSIRO Data61, Australia（澳大利亚CSIRO数据61）

Comments Accepted by ICCV 2025

2507.09305 2025-07-25 cs.CV cs.LG eess.IV

DAA*: Deep Angular A Star for Image-based Path Planning

Zhiwei Xu

机构 * School of Computing and Information Systems（计算与信息系统学院）； The University of Melbourne（墨尔本大学）； The Australian National University（澳大利亚国立大学）

Comments International Conference on Computer Vision (ICCV), 2025

2507.04599 2025-07-25 cs.CV

QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation

Jiahui Yang, Yongjia Ma, Donglin Di, Hao Li, Wei Chen, Yan Xie, Jianxun Cui, Xun Yang, Wangmeng Zuo

机构 * Harbin Institute of Technology（哈尔滨工业大学）； Li Auto（利汽车）； University of Science and Technology of China（中国科学技术大学）

Comments ICCV 2025, 30 pages, 26 figures

2507.01884 2025-07-25 cs.CV

Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification

Kunlun Xu, Fan Zhuo, Jiangmeng Li, Xu Zou, Jiahuan Zhou

机构 * Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）； University of Chinese Academy of Sciences（中国科学院大学）； School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）

Comments Accepted by ICCV 2025

2506.23825 2025-07-25 cs.CV

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

Haoji Zhang, Yiqin Wang, Yansong Tang, Yong Liu, Jiashi Feng, Xiaojie Jin

机构 * Tsinghua University（清华大学）； Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）； Beijing Jiaotong University（北京交通大学）； ByteDance Inc（字节跳动公司）

Comments Accepted by ICCV 2025

2503.13176 2025-07-25 cs.CV

DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction

Rui Wang, Quentin Lohmeyer, Mirko Meboldt, Siyu Tang

机构 * ETH Zürich（苏黎世联邦理工学院）

Comments Accepted by ICCV 2025

2503.11937 2025-07-25 cs.CV cs.AI

Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder

Wonwoong Cho, Yan-Ying Chen, Matthew Klenk, David I. Inouye, Yanxia Zhang

机构 * Purdue University（普渡大学）； Toyota Research Institute（丰田研究院）

Comments ICCV'25 (Highlight), The project page is available at https://tri-mac.github.io/att-adapter/

2503.08510 2025-07-25 cs.CV cs.LG

External Knowledge Injection for CLIP-Based Class-Incremental Learning

Da-Wei Zhou, Kai-Wen Li, Jingyi Ning, Han-Jia Ye, Lijun Zhang, De-Chuan Zhan

机构 * School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）； National Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家实验室，南京大学）

Comments Accepted to ICCV 2025. Code is available at: https://github.com/LAMDA-CL/ICCV25-ENGINE

2411.16319 2025-07-25 cs.CV

CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation

Leon Sick, Dominik Engel, Sebastian Hartwig, Pedro Hermosilla, Timo Ropinski

机构 * Ulm University（乌尔姆大学）； KAUST（科罗Swiss阿尔特姆大学）； TU Vienna（维也纳技术大学）

Comments Accepted at ICCV 2025. Project Page with Code, Models & Demo: https://leonsick.github.io/cuts3d/

2407.19795 2025-07-25 cs.CL cs.AI cs.CV

VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks

Juhwan Choi, Junehyoung Kwon, JungMin Yun, Seunguk Yu, YoungBin Kim

机构 * AITRICS Seoul（AITRICS首尔）； Chung-Ang University（Chung-ang 大学）

Comments ICCV 2025 Workshop on Curated Data for Efficient Learning (CDEL)