RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.
World-consistent video diffusion with explicit 3d modeling
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
support 1representative citing papers
A probabilistic graphical model called 3WM unifies 3D vision tasks into one system that performs them zero-shot by selecting different inference pathways through multimodal scene nodes.
citing papers explorer
-
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
RIGVid shows that filtered AI-generated videos can serve as effective supervision for complex robotic manipulation tasks without any real demonstrations.