Controllable Latent Space Augmentation for Digital Pathology
机构 * MICS, CentraleSupélec – Université Paris-Saclay（MICS，中央圣艾尔布兰理工大学——巴黎-萨克雷大学） ； Bioptimus, Inc.（Bioptimus公司） ； VitaDX International（VitaDX国际）
Comments Accepted at ICCV 2025
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model
机构 * National University of Singapore（国立新加坡大学） ； Nanjing University of Science and Technology（南京理工大学）
Comments ICCV 2025
MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion
机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Kuaishou Technology（快手科技）
Comments This paper is accepted by ICCV 2025
Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation
机构 * Graduate Center, CUNY（CUNY研究生中心） ； Hunter College, CUNY（CUNY霍普金斯学院） ； Weill Cornell Medicine（韦尔医学院）
Comments Accepted by ICCV 2025 Workshop on Recovering 6D Object Pose (R6D)
LaViPlan : Language-Guided Visual Path Planning with RLVR
机构 * Electronics and Telecommunications Research Institute（电子通信研究院）
Comments Accepted to the 2nd ICCV 2025 Workshop on the Challenge of Out-of-Label Hazards in Autonomous Driving (13 pages, 6 figures)
MMAD: Multi-label Micro-Action Detection in Videos
机构 * School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院） ； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院） ； ReLER, CCAI, Zhejiang University（浙江大学ReLER、CCAI）
Comments Accepted by ICCV 2025
