ICCV - arXivDaily 期刊&会议

2510.12795 2025-10-15 cs.CV cs.AI cs.LG math.AT stat.ML

CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations

Caner Korkmaz, Brighton Nuwagira, Barış Coşkunuzer, Tolga Birdal

Comments Appears at ICCV 2025

2510.12788 2025-10-15 cs.CV

Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report

Daniel Feijoo, Paula Garrido-Mellado, Marcos V. Conde, Jaesung Rim, Alvaro Garcia, Sunghyun Cho, Radu Timofte

机构 * Cidaut AI, Spain（Cidaut AI）； POSTECH, Korea（POSTECH）； University of Würzburg, Germany（乌尔姆大学）

Comments ICCV 2025 - AIM Workshop

2510.12765 2025-10-15 cs.CV

Efficient Perceptual Image Super Resolution: AIM 2025 Study and Benchmark

Bruno Longarela, Marcos V. Conde, Alvaro Garcia, Radu Timofte

机构 * Cidaut AI ； University of Würzburg（乌尔姆大学）； Computer Vision Lab（计算机视觉实验室）

Comments ICCV 2025 - AIM Workshop

2510.12387 2025-10-15 cs.CV

Scene Coordinate Reconstruction Priors

Wenjing Bian, Axel Barroso-Laguna, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann

机构 * Niantic Spatial ； University of Oxford（牛津大学）

Comments ICCV 2025, Project page: https://nianticspatial.github.io/scr-priors/

2510.12308 2025-10-15 cs.CV

Hybrid Gaussian Splatting for Novel Urban View Synthesis

Mohamed Omran, Farhad Zanjani, Davide Abati, Jens Petersen, Amirhossein Habibian

机构 * Qualcomm AI Research（高通人工智能研究）

Comments ICCV 2025 RealADSim Workshop

2510.12190 2025-10-15 cs.CV

Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos

Shingo Yokoi, Kento Sasaki, Yu Yamaguchi

机构 * Turing Inc.（图灵公司）

Comments 2nd Place Winner, ICCV 2025 2COOOL Competition

2510.11996 2025-10-15 cs.CV

Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning

Tanner Muturi, Blessing Agyei Kyem, Joshua Kofi Asamoah, Neema Jakisa Owor, Richard Dyzinela, Andrews Danyo, Yaw Adu-Gyamfi, Armstrong Aboah

机构 * University of Missouri–Columbia（密苏里大学哥伦比亚分校）； North Dakota State University（北达科他州立大学）； Texas A&M（德克萨斯农工大学）

Comments The paper was accepted at ICCV Conference 2025

2510.11962 2025-10-15 cs.LG cs.CV

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

Bowei Guo, Shengkun Tang, Cong Zeng, Zhiqiang Shen

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

Comments International Conference on Computer Vision, ICCV 2025

2510.11907 2025-10-15 cs.CV

Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis

Blessing Agyei Kyem, Neema Jakisa Owor, Andrews Danyo, Joshua Kofi Asamoah, Eugene Denteh, Tanner Muturi, Anthony Dontoh, Yaw Adu-Gyamfi, Armstrong Aboah

机构 * North Dakota State University（北达科塔州立大学）； University of Missouri–Columbia（密苏里大学哥伦比亚分校）； University of Memphis（孟菲斯大学）

Comments This paper was accepted at ICCV 2025

2510.10177 2025-10-15 cs.CV cs.AI

HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation

Yulin Wang, Mengting Hu, Hongli Li, Chen Luo

机构 * Southeast University（东南大学）； Purdue University（普渡大学）

Comments International Conference on Computer Vision, ICCV 2025 (Highlight) https://iccv.thecvf.com/virtual/2025/poster/338