zhan-xu/RigNet

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1519 stars · 205 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RigNet is a PyTorch implementation of the SIGGRAPH 2020 paper on neural rigging for articulated 3D characters. It takes a character mesh as input and automatically predicts a skeleton and skinning weights, outputting rigs that can be converted to FBX for use in animation tools.

Use cases

• automatically rig a 3d character mesh
• generate skeleton and skin weights from an obj file
• prepare articulated characters for animation
• convert static character models into rigged fbx files
• research on neural rigging and mesh analysis

When to choose

• you need to automate rigging of humanoid or articulated character meshes
• you want a research baseline or to build on neural rigging methods
• you can run PyTorch with CUDA on Linux or Windows

When to avoid

• you need a polished production tool with a GUI rather than research scripts
• your meshes cannot be simplified to 1K-5K vertices
• you need permissive licensing - the code is GPL-3.0

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision graphics animation computer-vision graphics machine-learning windows python character-rigging 3d-meshes siggraph pytorch research-code blender-addon game-development linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zhan-xu/RigNet")