OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
Perception-as-control: Fine-grained controllable image animation with 3d-aware motion representation,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.
citing papers explorer
-
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
-
Physical Object Understanding with a Physically Controllable World Model
Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.