CalciferZh/minimal-hand

Health v2 · maintenance only

Adoption not part of the score

1037 stars · 174 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library for real-time 3D hand motion capture from a single RGB camera, running at over 100fps. It combines a deep network (DetNet) for estimating joint locations with an inverse-kinematics network (IKNet) for estimating joint rotations.

Use cases

• capture hand motion from a webcam
• estimate 3D hand joint positions from RGB images
• get hand joint rotations for animation
• drive a hand avatar in Unity from a camera
• real-time hand tracking for VR or AR
• research on monocular 3D hand pose estimation

When to choose

• you need fast, real-time hand mocap with just a webcam
• you want plug-and-play pretrained models without training
• you need both joint locations and rotations
• you want to integrate hand tracking into a game engine or graphics pipeline

When to avoid

• you need to retrain or fine-tune the models (training code is not released)
• you need depth or multi-camera hand capture
• you need actively maintained software with recent updates
• you need a PyTorch implementation (the official code is TensorFlow-based)

Facets

library · maturity maintenance

computer-vision machine-learning deep-learning computer-vision deep-learning graphics python windows hand-pose-estimation hand-tracking motion-capture rgb-camera mano 3d-pose-estimation real-time linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="CalciferZh/minimal-hand")