日常動画から関節物体を再構成し操作を再現する実-to-シミュレーション手法
Track, Articulate, Act: Generating Articulation from Casual Human Videos
単眼RGB動画から、ドアや引き出しなどの関節物体のリンク分割・関節推定・3D再構成を行い、手の動きと合わせてシミュレーション上で操作を再現するフレームワークを提案。
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: Jiaming Zhang, Homanga Bharadhwaj
分類: cs.CV
原文アブストラクト
Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes in object state. In this work, we study articulated objects such as doors, drawers, cabinets, laptops, ovens, and hinged containers that are ubiquitous in daily life and present unique challenges for embodied interaction. These objects cannot be represented by a single pose; their motion depends on the underlying parts and joints. We introduce a real-to-sim framework that reconstructs a simulation-ready articulated object and hand-object interaction from a casual monocular RGB video, without RGB-D or multi-view input, prior scans, manually specified joints, or robot demonstrations. Our key insight is that dense 3D point tracks provide an embodiment-agnostic articulation cue: points on the fixed link remain approximately stationary, while points on the moving link follow coherent revolute or prismatic motion. Our method segments the links, estimates the joint and its state trajectory, reconstructs an articulated asset, and aligns the recovered 3D hand motion with the object. Central to our approach is a modular recipe that repurposes powerful pretrained models for single-image 3D reconstruction, mesh segmentation, and 3D scene flow, connecting their predictions through explicit geometric reasoning to infer articulation. We use the reconstructed articulated object and the human hand trajectory to replay interactions through contact in MuJoCo. The framework shows how pretrained vision models and explicit motion reasoning can turn casual human videos into articulated object models suitable for downstream embodied interactions. https://track-articulate-act.github.io/
関連論文
- チャンク型VLAマニピュレーションポリシーの学習と実機展開のためのSim-to-Real統合パイプラインsim2real
- 運動学を超えて:筋駆動模倣学習のためのシミュレーション忠実度ベンチマークsim2real
- CRISP: 多様な形状と接触ソルバを備えた接触リッチロボットシミュレーション基盤sim2real
- 同じ世界、異なる知識:孤立評価が世界モデルの修復を誤判定するときsim2real
- DEXTERA: 単一画像から実機展開可能な巧みなマニピュレーションへ向けたReal-to-Sim-to-Realsim2real
- 単一スキャンからのガウシアンスプラッティングによる実演合成と視覚運動ポリシー学習sim2real