PeizhuoLi/neural-blend-shapes
An end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool [SIGGRAPH 2021]
This project helps 3D animators and character artists automatically prepare 3D character models for animation. You provide a static 3D mesh (like an .obj file) and a desired pose sequence, and it generates an animated 3D model (like an .fbx file) with a skeleton, skinning, and blend shapes. This streamlines the technical setup for creating realistic character movements.
700 stars. No commits in the last 6 months.
Use this if you need to quickly rig, skin, and generate blend shapes for biped 3D character models to prepare them for animation.
Not ideal if you need to animate non-biped characters, require highly customized rigging, or prefer manual control over every rigging detail.
Stars
700
Forks
98
Language
Python
License
—
Category
Last pushed
Aug 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PeizhuoLi/neural-blend-shapes"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MarcoForte/FBA_Matting
Official repository for the paper F, B, Alpha Matting
pypose/pypose
A library for differentiable robotics on manifolds.
snap-research/articulated-animation
Code for Motion Representations for Articulated Animation paper
foamliu/Deep-Image-Matting
Deep Image Matting
dyelax/Adversarial_Video_Generation
A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by...