動的物体の世界を振り付ける：CHORD
Choreographing a World of Dynamic Objects
2D動画の生成モデルからラグランジュ運動情報を蒸留し、カテゴリに依存せず多様な4D動的シーンを生成する手法を提案。ロボットマニピュレーション方策の生成にも応用可能。
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: Yanzhe Lyu, Chen Geng, Karthik Dharmarajan, Yunzhi Zhang, Hadi Alzayer, Shangzhe Wu, Jiajun Wu
分類: cs.CV, cs.GR, cs.RO
原文アブストラクト
Dynamic objects in our physical 4D (3D + time) world are constantly evolving, deforming, and interacting with other objects, leading to diverse 4D scene dynamics. In this paper, we present a universal generative pipeline, CHORD, for CHOReographing Dynamic objects and scenes and synthesizing this type of phenomena. Traditional rule-based graphics pipelines to create these dynamics are based on category-specific heuristics, yet are labor-intensive and not scalable. Recent learning-based methods typically demand large-scale datasets, which may not cover all object categories in interest. Our approach instead inherits the universality from the video generative models by proposing a distillation-based pipeline to extract the rich Lagrangian motion information hidden in the Eulerian representations of 2D videos. Our method is universal, versatile, and category-agnostic. We demonstrate its effectiveness by conducting experiments to generate a diverse range of multi-body 4D dynamics, show its advantage compared to existing methods, and demonstrate its applicability in generating robotics manipulation policies. Project page: https://yanzhelyu.github.io/chord
