akashsengupta1997/HierarchicalProbabilistic3DHuman

Code repository for the paper: Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild (ICCV 2021)

37
/ 100
Emerging

This project helps researchers analyze human motion by reconstructing detailed 3D body shapes and poses from standard 2D images. You input a picture of a person, and it outputs multiple likely 3D models showing their body shape and posture, including an estimation of how uncertain the model is. It's designed for researchers working on understanding and modeling human movement.

204 stars. No commits in the last 6 months.

Use this if you are a researcher needing to convert 2D images of people into accurate 3D kinematic models for analysis, especially when considering multiple plausible poses.

Not ideal if you need real-time performance for live applications or if you are not comfortable with command-line tools and academic-style software.

human-motion-analysis 3D-reconstruction computer-vision-research kinematics pose-estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

204

Forks

12

Language

Python

License

MIT

Last pushed

Feb 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/akashsengupta1997/HierarchicalProbabilistic3DHuman"

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