GEM-4D improves video world models for robot manipulation by distilling 4D geometric correspondences into training and adding an inverse dynamics module, achieving SOTA geometric consistency and 81% real-world success.
In: Interna- tional Conference on 3D Vision (3DV) (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
GEM-4D improves video world models for robot manipulation by distilling 4D geometric correspondences into training and adding an inverse dynamics module, achieving SOTA geometric consistency and 81% real-world success.