Imagine2Real is a zero-shot humanoid-object interaction method that unifies robot and object motion as 4D point trajectories, tracks only sparse keypoints inside a behavior foundation model latent space, and trains with simple rewards for direct mocap deployment.
Dexman: Learning bimanual dexterous manipulation from human and generated videos.arXiv preprint, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
Imagine2Real is a zero-shot humanoid-object interaction method that unifies robot and object motion as 4D point trajectories, tracks only sparse keypoints inside a behavior foundation model latent space, and trains with simple rewards for direct mocap deployment.