# digital-standard/ThreeDPoseTracker

Repository: https://github.com/digital-standard/ThreeDPoseTracker
Canonical: https://ross.abutalabs.com/products/threedposetracker
Language: C#
License Family: other
Last push: 2021-10-04T02:34:10+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2364, "days_push": 1795, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1042, forks 174 (observed 2026-08-28T04:03:20.802017+00:00)

## What it is
A Unity-based Windows application that estimates 3D human pose from video or webcam input using an ONNX neural network model via Unity Barracuda, and drives a 3D avatar (VRM) with the tracked motion. It supports BVH export and OSC output for use with external tools.

## Use cases
- track 3d human pose from a webcam
- drive a vrm avatar with body motion capture
- export motion capture as bvh files
- vtuber full-body tracking without special hardware
- run pose estimation on video files

## When to choose
- you want free webcam-based 3d pose tracking on Windows 10 with an NVIDIA GPU
- you need a Unity project to experiment with onnx pose models and VRM avatars

## When to avoid
- you need maintained software or support - the project is explicitly unmaintained and moved to a private repo
- you are on macOS or Linux - only Windows 10 is confirmed
- you need commercial use - the license is non-commercial

## Facets
- artifact type: application
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing, animation
- domain: computer-vision, machine-learning, graphics, media
- platform: windows
- tags: pose-estimation, unity, onnx, barracuda, vtuber, motion-capture, 3d-avatar, unmaintained, desktop

## Member repositories
- digital-standard/ThreeDPoseTracker (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.802017+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 2026-08-30T07:02:37.419107+00:00, confidence not recorded.
  - readme: https://github.com/digital-standard/ThreeDPoseTracker (fetched 2026-08-28T04:03:20.802017+00:00, sha ab7090b73adb)
- Data as of 2026-08-30T08:39:29.467469+00:00.