manotorch
lixiny
A differentiable MANO hand-model layer with anatomical hand utilities in PyTorch.
What you can explore
Explore human hand pose and shape representations before retargeting to a robot.
Before you use it
MANO model files must be obtained under their own agreement. A human model does not describe robot joints or actuator limits.
Original contributors
Lixin Yang and contributors
License / access: Code: Apache 2.0 · MANO models have separate, restricted terms
Keep exploring
manopth
A PyTorch implementation of the MANO hand-model layer for differentiable hand reconstruction.
HaMeR
Transformer-based reconstruction of three-dimensional human hand meshes from images.
Dex Retargeting
Software for mapping human hand motion to the joint configurations of robotic hands.
Editorial reference · checked 2026-09-22