Report
Estimating SE(3) transforms from video could help turn generated video into robot actions
A user highlights NeurIPS work on estimating SE(3) transforms from video and suggests a possible robotics use.
TLDR
A user points to researchers’ NeurIPS work on estimating SE(3) transforms from video. They suggest the method could help turn output from generative video models into executable 3D robot actions.
Combined views
5.5K
1 Source, first seen ago