物体中心の世界モデルを大規模3D全物体フローデータセットでスケールアップするObjectWorld
ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset
物体表面全体（遮蔽領域含む）に密な3D軌道を割り当てる「3D全物体フロー」表現と、1210時間の大規模データセットを構築し、画像とタスク記述から全物体フローを予測する世界モデルを学習した研究。
著者: Haonan Chen, Sicheng Isabella Lu, Haitian Li, Jiajin Wu, Hexiang Wei, Jiawei Zhang, Xin Fei, Yiwen Hou, Chenrui Tie, Chongkai Gao, Sheng Wang, Lin Shao
分類: cs.RO
原文アブストラクト
Generative world modeling from large-scale visual data offers a promising path toward scalable robot manipulation. This calls for an intermediate representation that can be supervised at scale and remains actionable for downstream control. We propose 3D full-object flow, an object-centric motion representation that assigns dense 3D trajectories to points across the complete surface of a target object, including its occluded regions. By extending visible-surface object flow to the full object geometry, this representation makes complete object motion explicit and applies uniformly to both rigid and deformable objects. To realize the potential of this representation at scale, we introduce a 1210-hour full-object flow dataset that addresses the scarcity of large-scale supervision for complete 3D object motion. The dataset integrates diverse real-world videos and physical simulations, with a scalable annotation pipeline for recovering full-object motion from real-world observations and quality metrics for systematically assessing annotation quality. We then train a world model that takes an image and a task description as input and predicts dense full-object flow over the reconstructed object geometry. Experiments show reliable annotation quality, data-scalable flow prediction, and effective downstream manipulation across novel scenes and robot embodiments. Project website with additional results and videos: https://nus-lins-lab.github.io/ObjectWorld/.