ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset
ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset
This paper proposes 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 occluded regions. The authors introduce a 1210-hour full-object flow dataset integrating diverse real-world videos and physical simulations with a scalable annotation pipeline. A world model is trained to predict this flow from images and task descriptions, demonstrating reliable annotation quality, data-scalable flow prediction, and effective downstream manipulation across novel scenes and robot embodiments.
The authors introduce a new object-centric motion representation called 3D full-object flow and release a corresponding dataset comprising 1210 hours of data to support scalable supervision for complete 3D object motion, including occluded regions.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported duration
1,210 hours
View original evidence
lete 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
Open source S3
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
lete 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
Open source S3
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org