sinzlab/platypose

Official Implementation for "Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation"

15
/ 100
Experimental

This tool helps researchers and engineers analyze human movement by generating multiple possible 3D human motion estimations from input data. It takes in observational data or specific conditions you define and outputs various calibrated 3D pose samples, allowing for comprehensive analysis of motion in different scenarios. It's designed for professionals working in fields like biomechanics, animation, or human-computer interaction.

No commits in the last 6 months.

Use this if you need to understand or simulate diverse 3D human motions based on limited information, especially when there isn't a single obvious answer.

Not ideal if you require real-time tracking of 3D human motion with immediate, high-fidelity singular pose estimates without exploring multiple possibilities.

biomechanics motion-analysis animation human-factors robotics
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Jupyter Notebook

License

Last pushed

May 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sinzlab/platypose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.