H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos

作者：Hai Ci, Xiaokang Liu, Pei Yang, Yiren Song, Mike Zheng Shou · 单位：Show Lab, National University of Singapore · 会议/期刊：CVPRW 2025 · 日期：2025-12-10 · 来源：High-Level Structured Planning / Video-based Planning