ICCV

Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables

Wontae Kim, Keuntek Lee, Nam Ik Cho

机构 * IPAI, Seoul National University, Seoul, Korea（IPAI，首尔国立大学，首尔，韩国） ； LG Electronics, Seoul, Korea（LG电子，首尔，韩国） ； Department of ECE, INMC, Seoul National University, Seoul, Korea（电子工程系，INMC，首尔国立大学，首尔，韩国） 纠错

Comments Accepted by ICCV 2025

ViT-FIQA: Assessing Face Image Quality using Vision Transformers

Andrea Atzori, Fadi Boutros, Naser Damer

机构 * Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究 institutes IGD） ； Department of Computer Science, TU Darmstadt（图腾大学计算机科学系） 纠错

Comments Accepted at the IEEE/CVF International Conference on Computer Vision Workshops 2025 (ICCVW 2025)

Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models

Xinyu Chen, Haotian Zhai, Can Zhang, Xiupeng Shi, Ruirui Li

机构 * Shanghai University（上海大学） ； Beijing University of Chemical Technology（北京化工大学） ； University of Minnesota（明尼苏达大学） 纠错

Comments Accepted by ICCV 2025

Improving U-Net Confidence on TEM Image Data with L2-Regularization, Transfer Learning, and Deep Fine-Tuning

Aiden Ochoa, Xinyuan Xu, Xing Wang

机构 * Department of Nuclear Engineering, Penn State University（核工程系，宾夕法尼亚州立大学） 纠错

Comments Accepted into the ICCV 2025 CV4MS Workshop

Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation

Hiroyasu Akada, Jian Wang, Vladislav Golyanik, Christian Theobalt

机构 * Max Planck Institute for Informatics（马克斯·普朗克信息研究所） 纠错

Comments Project page: https://4dqv.mpi-inf.mpg.de/EgoRear/

Journal ref International Conference on Computer Vision 2025 (ICCV 2025)

LBM: Latent Bridge Matching for Fast Image-to-Image Translation

Clément Chadebec, Onur Tasar, Sanjeev Sreetharan, Benjamin Aubin

机构 * Jasper Research（杰斯珀研究） 纠错

Comments Accepted to ICCV 2025