Researchers develop world model forecasting videos from arbitrary viewpoints
Researchers developed a world model that takes multi-view video histories and language instructions to forecast future videos from arbitrary viewpoints and 3D trajectories of scene points.
The model extends a pretrained world model with camera-conditioned multi-view processing and adds a trajectory head that predicts how physical points move through time.
In simulated and real-robot experiments, using point supervision raised the manipulation success of the action-enabled model.
Sources behind this report
- Hugging Face
Research · abstract · CC0 1.0
Source published
Read by the newsroom
Report history
No earlier revision dates are retained here. This does not establish that the report has never changed; read any dated updates and corrections.
This brief was made by AI and checked against its cited public sources. How the newsroom works