Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

The paper introduces RoboTryOn, a method that transforms human egocentric videos into synthetic demonstrations for robots by virtually swapping the human with a target robot while preserving task, objects, and background. It uses autoregressive keyframe translation guided by human hand skeletons and an inverse dynamics model to generate action labels for policy learning. Experiments on various humanoid robots show that policies trained on these synthetic videos achieve up to 60% success on new tasks, matching teleoperated demonstration performance at roughly one‑third the cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• robotics