# digital-standard/ThreeDPoseUnityBarracuda

Unity sample of 3D pose estimation using Barracuda

Repository: https://github.com/digital-standard/ThreeDPoseUnityBarracuda
Canonical: https://ross.abutalabs.com/products/threedposeunitybarracuda
Language: C#
License Family: other
Last push: 2022-01-18T06:15:32+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2394, "days_push": 1688, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1517, forks 279 (observed 2026-08-28T04:04:56.692163+00:00)

## What it is
A Unity sample project that performs real-time 3D human pose estimation from video using an ONNX model loaded via Unity Barracuda, driving an avatar to mirror a person's motion. It is explicitly unmaintained and provided as-is.

## Use cases
- estimate 3d human pose from video in unity
- real-time motion capture driving a unity avatar
- run onnx pose estimation model with barracuda
- single-person 3d pose tracking demo
- vtuber-style avatar motion from webcam

## When to choose
- you need a reference implementation of 3D pose estimation in Unity with Barracuda
- you want to drive a single avatar from video in real time on a GPU machine

## When to avoid
- you need maintained or supported software
- you need multi-person pose estimation
- you lack a discrete GPU
- you need a production-ready motion capture solution

## Facets
- artifact type: application
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing, llm-inference
- domain: computer-vision, machine-learning, graphics
- platform: windows
- tags: unity, pose-estimation, barracuda, onnx, motion-capture, 3d-pose, vtuber, sample-project, game-development, desktop, gpu

## Member repositories
- digital-standard/ThreeDPoseUnityBarracuda (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:56.692163+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 2026-08-30T04:32:04.173444+00:00, confidence not recorded.
  - readme: https://github.com/digital-standard/ThreeDPoseUnityBarracuda (fetched 2026-08-28T04:04:56.692163+00:00, sha 1bf713698a1c)
- Data as of 2026-08-30T08:39:29.467469+00:00.