期刊&会议

ICCV

International Conference on Computer Vision · 会议 · Computer Vision

2025-10-03 至 2025-10-03 共收录 5 篇

2510.02314 2025-10-03 cs.CV

StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

Bo-Hsu Ke, You-Zhe Xie, Yu-Lun Liu, Wei-Chen Chiu

机构 * National Yang Ming Chiao Tung University（阳明交通大学）

Comments ICCV 2025. Project page: https://hentci.github.io/stealthattack/

2510.02313 2025-10-03 cs.CV

Clink! Chop! Thud! -- Learning Object Sounds from Real-World Interactions

Mengyu Yang, Yiming Chen, Haozheng Pei, Siddhant Agarwal, Arun Balajee Vasudevan, James Hays

机构 * Georgia Institute of Technology（佐治亚理工学院）； Carnegie Mellon University（卡内基梅隆大学）

Comments ICCV 2025. Project page: https://clink-chop-thud.github.io/

2510.01576 2025-10-03 cs.CV cs.AI cs.HC

Guiding Multimodal Large Language Models with Blind and Low Vision People Visual Questions for Proactive Visual Interpretations

Ricardo Gonzalez Penuela, Felipe Arias-Russi, Victor Capriles

Comments 7 pages, 2 figure, 2 tables, CV4A11y Workshop at ICCV 2025

2508.12082 2025-10-03 cs.CV cs.AI cs.LG

Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability

Seungju Yoo, Hyuk Kwon, Joong-Won Hwang, Kibok Lee

机构 * Yonsei University（延世大学）； ETRI（电子技术研究所）

Comments ICCV 2025 Oral; v2: fixed a typo in the title and updated experimental results

2505.05288 2025-10-03 cs.CV cs.AI cs.RO

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

Ahmed Abdelreheem, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Abdelrahman Eldesokey, Peter Wonka, Gabriel Brostow, Sara Vicente, Guillermo Garcia-Hernando

机构 * Niantic Spatial ； KAUST（科威特科学与技术研究中心）； UCL（伦敦大学学院）

Comments ICCV 2025. Project page: https://nianticlabs.github.io/placeit3d/