HavenFeng/ArtEq
Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance (ICCV2023)
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.
Stars
54
Forks
4
Language
Python
License
—
Category
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.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.