GIRAF: 関節物体との汎用的な人間インタラクションの実現
GIRAF: Towards Generalizable Human Interactions with Articulated Objects
関節を持つ物体との全身インタラクションを生成するテキスト条件付き拡散モデルを提案し、物体中心表現と混合ドメイン学習、接触ベースのデータ拡張により未見の物体構成への汎化を実現した。
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: Xiaohan Zhang, Sebastian Starke, Alexander Winkler, Federica Bogo, Samir Aroudj, Yuting Ye
分類: cs.CV
原文アブストラクト
Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications in robotics training and virtual agents. Existing models remain limited: some focus on simple activities with static objects, while others restrict attention to hand-only manipulation. This leaves open the problem of generating coordinated full-body motion that approaches, manipulates, and moves articulated objects in a realistic and generalizable way. The key difficulty lies in reasoning jointly about locomotion, fine-grained contact, and object articulation. Models must capture subtle hand-object correspondences that transfer across object geometries, while also producing seamless transitions from navigation to manipulation. At the same time, the scarcity of large-scale paired motion-scene data makes it difficult to generalize across diverse object positions and shapes. We introduce a text-conditioned diffusion model that addresses these challenges through three core ideas: an object-centric representation that unifies hand-object contact with object surfaces, a mixed-domain training strategy that balances locomotion and interaction, and a contact-based augmentation scheme that expands training diversity. Through experiments, our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.
