Do as I Do: Dexterous Data from Human Videos

Loading video
Loading videoDo as I Do reconstructs hand-object interactions from monocular RGB videos and retargets them into executable multi-fingered manipulation trajectories.
Category: arm
Author: @notmahi
Date: 2026-06-18T00:00:00
Duration: 55.7s
Reference: https://arxiv.org/abs/2606.19333





