manopth
hassony2
A PyTorch implementation of the MANO hand-model layer for differentiable hand reconstruction.
What you can explore
Inspect pose parameters, mesh generation and integration with hand-perception research.
Before you use it
Documented dependencies are old. MANO assets require separate access and permissions; they are not included under the code license.
Original contributors
Yana Hasson and contributors
License / access: Code: GPL 3.0 · MANO model license is separate
Keep exploring
manotorch
A differentiable MANO hand-model layer with anatomical hand utilities in PyTorch.
HOLD
Joint reconstruction of a hand and a held object from video.
HO-3D
Images and three-dimensional annotations of a human hand manipulating objects under occlusion.
Editorial reference · checked 2026-09-22