VAST-AI-Research/UniRig

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1783 stars · 175 forks observed · 2026-10-02

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

UniRig is the official implementation of a SIGGRAPH 2025 framework that automatically rigs 3D models by predicting skeletons and skinning weights using large autoregressive models with a bone-point cross-attention mechanism. It includes the Rig-XL dataset of over 14,000 rigged 3D models and significantly outperforms prior academic and commercial rigging methods.

Use cases

• automatically rig a 3D character model for animation
• generate a skeleton for a 3D mesh without manual work
• predict skinning weights for anime or animal models
• speed up a 3D animation pipeline with auto-rigging
• rig diverse 3D models from AI generation or traditional workflows
• train or evaluate skeleton prediction models on the Rig-XL dataset

When to choose

• you need automated skeleton and skinning for diverse 3D models like humans, animals, or fictional characters
• your 3D assets have complex or non-standard topologies that break simpler auto-rigging tools
• you want state-of-the-art rigging accuracy backed by a published SIGGRAPH 2025 method
• you are building an AI 3D content creation pipeline and need rigging as a step

When to avoid

• you need fine artistic control over hand-placed bones in a tool like Blender or Maya
• you only need to rig simple humanoid characters where existing DCC auto-rig tools suffice
• you lack a GPU or cannot run large autoregressive model inference
• you need production skinning quality beyond what automated methods provide without cleanup

Facets

library · maturity active

machine-learning deep-learning animation graphics llm-inference computer-vision graphics machine-learning artificial-intelligence python auto-rigging 3d-graphics skeleton-generation skinning-weights autoregressive-models siggraph-2025 3d-animation linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="VAST-AI-Research/UniRig")