digital-standard/ThreeDPoseUnityBarracuda

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1517 stars · 279 forks observed · 2026-08-28

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

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

application · maturity abandoned

machine-learning computer-vision image-processing llm-inference computer-vision machine-learning graphics windows unity pose-estimation barracuda onnx motion-capture 3d-pose vtuber sample-project game-development desktop gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="digital-standard/ThreeDPoseUnityBarracuda")