HavenFeng/ArtEq

Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance (ICCV2023)

33
/ 100
Emerging

This project helps researchers and engineers quickly create a 3D digital model of a human body from a 3D scan or point cloud data. It takes raw 3D point cloud scans of a person in various poses and outputs a highly accurate, animatable SMPL (Skinned Multi-Person Linear) body model. This is for professionals in computer vision, animation, or robotics who need to reconstruct human shapes and poses efficiently and accurately from 3D data.

No commits in the last 6 months.

Use this if you need to generate realistic 3D human body models from point cloud data, especially when dealing with many diverse or previously unseen body poses, and require fast inference.

Not ideal if your work involves commercial applications, as this software is strictly for non-commercial scientific research.

3D-human-reconstruction computer-vision motion-capture animation robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

54

Forks

4

Language

Python

License

Last pushed

Apr 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HavenFeng/ArtEq"

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