ICCV

Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition

Pulkit Kumar, Shuaiyi Huang, Matthew Walmer, Sai Saketh Rambhatla, Abhinav Shrivastava

机构 * University of Maryland, College Park（马里兰大学学院公园分校） 纠错

Comments Accepted at ICCV 2025; First two authors contributed equally

MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy

Wuyang Li, Wentao Pan, Xiaoyuan Liu, Zhendong Luo, Chenxin Li, Hengyu Liu, Din Ping Tsai, Mu Ku Chen, Yixuan Yuan

机构 * The Chinese University of Hong Kong（香港中文大学） ； City University of Hong Kong（香港城市大学） ； EPFL（苏黎世联邦理工学院） 纠错

Comments ICCV 2025 (Highlight); Project Page: https://cuhk-aim-group.github.io/MetaScope/

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models

Hyungjin Kim, Seokho Ahn, Young-Duk Seo

机构 * Department of Electrical and Computer Engineering, Inha University（电子与计算机工程系，inha大学） 纠错

Comments Accepted at ICCV 2025

Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility

Melih Barsbey, Lucas Prieto, Stefanos Zafeiriou, Tolga Birdal

机构 * Imperial College London（伦敦帝国学院） 纠错

Comments Accepted at ICCV 2025, 25 pages

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Pingchuan Ma, Xiaopei Yang, Yusong Li, Ming Gui, Felix Krause, Johannes Schusterbauer, Björn Ommer

机构 * Munich Center for Machine Learning (MCML)（慕尼黑機器學習中心） 纠错

Comments ICCV 2025, Project Page: https://compvis.github.io/SCFlow/

ChartCap: Mitigating Hallucination of Dense Chart Captioning

Junyoung Lim, Jaewoo Ahn, Gunhee Kim

机构 * Seoul National University（首尔国立大学） 纠错

Comments ICCV 2025 (Highlight)

H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction

Heng Jia, Linchao Zhu, Na Zhao

机构 * ReLER Lab, CCAI, Zhejiang University（浙江大学ReLER实验室，中国计算机协会，浙江大学） ； The State Key Lab of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能国家重点实验室） ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

Comments ICCV 2025

Adversarial Attention Perturbations for Large Object Detection Transformers

Zachary Yahn, Selim Furkan Tekin, Fatih Ilhan, Sihao Hu, Tiansheng Huang, Yichang Xu, Margaret Loper, Ling Liu

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Georgia Tech Research Institute（佐治亚理工研究 institute） 纠错

Comments ICCV 2025

AQUAH: Automatic Quantification and Unified Agent in Hydrology

Songkun Yan, Zhi Li, Siyu Zhu, Yixin Wen, Mofan Zhang, Mengye Chen, Jie Cao, Yang Hong

Comments 8 pages, 5 figures, 2025 ICCV SEA workshop paper

How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes

Mahnoor Fatima Saad, Ziad Al-Halah

机构 * University of Utah（犹他大学） 纠错

Comments Accepted to ICCV 2025. Project Page: https://mahnoor-fatima-saad.github.io/m-capa.html

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

Shuangkang Fang, I-Chao Shen, Yufeng Wang, Yi-Hsuan Tsai, Yi Yang, Shuchang Zhou, Wenrui Ding, Takeo Igarashi, Ming-Hsuan Yang

机构 * Beihang University（北航大学） ； The University of Tokyo（东京大学） ； Atmanity Inc.（Atmanity公司） ； StepFun Inc.（StepFun公司） ； UC Merced（加州大学默塞德分校） 纠错

Comments Accepted by ICCV. Project Website: https://sk-fun.fun/MeshLLM

AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving

Jiawei Xu, Kai Deng, Zexin Fan, Shenlong Wang, Jin Xie, Jian Yang

机构 * College of Computer Science, Nankai University（南开大学计算机科学学院） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院） 纠错

Comments Accepted by ICCV 2025

Style Composition within Distinct LoRA modules for Traditional Art

Jaehyun Lee, Wonhark Park, Wonsik Shin, Hyunho Lee, Hyoung Min Na, Nojun Kwak

机构 * Seoul National University（首尔国立大学） ； Kyunghee University（庆熙大学） 纠错

Comments Accepted to ICCV 2025 Workshop(WCCA)

Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation

Xiuyu Yang, Shuhan Tan, Philipp Krähenbühl

机构 * UT Austin（德克萨斯大学奥斯汀分校） 纠错

Comments ICCV 2025. Project page: https://orangesodahub.github.io/InfGen Code: https://github.com/OrangeSodahub/infgen

EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs

Ivan Rodin, Tz-Ying Wu, Kyle Min, Sharath Nittur Sridhar, Antonino Furnari, Subarna Tripathi, Giovanni Maria Farinella

机构 * University of Catania（卡塔尼亚大学） ； Intel Labs（英特尔实验室） 纠错

Comments Accepted to SAUAFG Workshop at ICCV 2025

PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

Ciyu Ruan, Ruishan Guo, Zihang Gong, Jingao Xu, Wenhan Yang, Xinlei Chen

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Harbin Institute of Technology（哈尔滨工业大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Pengcheng Laboratory（鹏城实验室） 纠错

Comments This version is the camera-ready version accepted at ICCV 2025

JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers

Kwon Byung-Ki, Qi Dai, Lee Hyoseok, Chong Luo, Tae-Hyun Oh

机构 * POSTECH ； Microsoft Research Asia（微软亚洲研究院） ； KAIST（韩国科学技术院） 纠错

Comments Accepted to IEEE/CVF International Conference on Computer Vision (ICCV) 2025. Project page: https://byungki-k.github.io/JointDiT/ Code: https://github.com/kaist-ami/JointDiT

FlowR: Flowing from Sparse to Dense 3D Reconstructions

Tobias Fischer, Samuel Rota Bulò, Yung-Hsu Yang, Nikhil Keetha, Lorenzo Porzi, Norman Müller, Katja Schwarz, Jonathon Luiten, Marc Pollefeys, Peter Kontschieder

机构 * ETH Zürich（苏黎世联邦理工学院） ； Meta Reality Labs Zürich（Meta现实实验室（苏黎世）） ； CMU（卡内基梅隆大学） 纠错

Comments ICCV 2025 Highlight. Project page is available at https://tobiasfshr.github.io/pub/flowr

Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer

Qingyu Shi, Jianzong Wu, Jinbin Bai, Jiangning Zhang, Lu Qi, Yunhai Tong, Xiangtai Li

机构 * PKU（北京大学） ； NTU（国立新加坡大学） ； NUS（新加坡国立大学） ； ZJU（浙江大学） ； UC Merced（加州大学默塞德分校） 纠错

Comments ICCV 2025

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Ho Kei Cheng, Alexander Schwing

Comments ICCV 2025. Project page: https://hkchengrex.github.io/C2OT

IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features

Anand Kumar, Jiteng Mu, Nuno Vasconcelos

机构 * University of California, San Diego（加州大学圣地亚哥分校） 纠错

Comments 17 pages, 16 figures

Journal ref Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) 2025

EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision

Dmitrii Torbunov, Yihui Ren, Animesh Ghose, Odera Dim, Yonggang Cui

机构 * Brookhaven National Laboratory（布鲁克海文国家实验室） 纠错

Comments Accepted to ICCV 2025

Learning Interpretable Queries for Explainable Image Classification with Information Pursuit

Stefan Kolek, Aditya Chattopadhyay, Kwan Ho Ryan Chan, Hector Andrade-Loarca, Gitta Kutyniok, Réne Vidal

机构 * LMU Munich（慕尼黑大学） ； AWS AI Labs（AWS人工智能实验室） ； University of Pennsylvania（宾夕法尼亚大学） ； Technical University of Munich（慕尼黑技术大学） ； Munich Center of Machine Learning（慕尼黑机器学习中心） 纠错

Comments Published at ICCV 2025