# CalciferZh/minimal-hand

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Repository: https://github.com/CalciferZh/minimal-hand
Canonical: https://ross.abutalabs.com/products/minimal-hand
Language: Python
License: MIT
License Family: permissive
Topics: computer-vision, deep-learning, 3d-hand-pose-estimation, hand-tracking, hand-motion-capture
Last push: 2022-01-12T12:48:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2368, "days_push": 1694, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1037, forks 174 (observed 2026-08-28T04:03:19.387913+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: computer-vision, deep-learning, graphics
- platform: python, windows
- tags: hand-pose-estimation, hand-tracking, motion-capture, rgb-camera, mano, 3d-pose-estimation, real-time, linux, macos

## Member repositories
- CalciferZh/minimal-hand (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.387913+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:19.951792+00:00, confidence not recorded.
  - readme: https://github.com/CalciferZh/minimal-hand (fetched 2026-08-28T04:03:19.387913+00:00, sha e5033f39d92b)
- Data as of 2026-08-30T08:39:29.467469+00:00.