DEXTEROUS MANIPULATION

The world of dexterous hands.

Compare hardware. Discover applications. Share what works. An open reference and community for dexterous manipulation.

EgoInfinity

Rice-RobotPI-Lab

A reconstruction pipeline for recovering metric hand–object interaction from RGB video.

What you can explore

Explore geometry and motion recovery as preparation for human-to-robot transfer.

Before you use it

Calibration and reconstruction quality affect the resulting motion. Check separate restrictions for MANO and pretrained components.

Original contributors

Gaotian Wang, Kejia Ren, Andrew Morgan and collaborators

License / access: Project code: MIT as stated by authors · external models have separate licenses

Original code & documentation

Keep exploring

HaWoR

Reconstruction of world-space hand motion from egocentric video.

HOLD

Joint reconstruction of a hand and a held object from video.

DexMachina

Physics-based retargeting of human demonstrations into coordinated robot-hand manipulation of articulated objects.

Editorial reference · checked 2026-09-22

Start a discussion

Published posts are public. First contributions are reviewed. Only share material you have permission to disclose.

Report a post