V2P-Manip: 単眼人間ビデオからの器用操作学習
V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos
単眼の人間デモビデオから、視覚的忠実度と物理的妥当性を両立した軌道を抽出し、器用な操作ポリシーを直接学習するフレームワークを提案。3Dアセット取得、軌道推定、ポリシー学習を統合し、二段階の精緻化で空間整合性と物理一貫性を確保する。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kaihan Chen, Yanming Shao, Haifeng Ji, Xiaokang Yang, Yao Mu
分類: cs.RO, cs.CV
原文アブストラクト
Achieving autonomous robotic dexterous manipulation requires precise, human-like action sequences at scale. As a scalable supplement to costly teleoperation data, extracting trajectories with both visual fidelity and physical plausibility from monocular videos represents a promising frontier in embodied AI. To this end, we introduce V2P-Manip, an efficient framework designed to learn dexterous manipulation policies directly from human demonstration videos. We establish an efficient, integrated pipeline encompassing 3D asset acquisition, trajectory estimation, and dexterous policy learning. To bridge the gap between visual perception and physical constraints, we introduce a two-stage refinement process to enforce spatial alignment and physical consistency. Evaluations on the TACO and OakInk benchmarks demonstrate that our approach significantly outperforms previous methods in pose accuracy, adaptability to unstructured environments, and training efficiency. Ultimately, experimental results confirm an average success rate of over 75% across multiple synthetic manipulation tasks and validate the adaptability of the extracted manipulation priors across diverse dexterous hand embodiments.
