Oriel — AI & technology worth noticing, every day.

One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

Paper · https://arxiv.org/abs/2504.12451

The rapid evolution of 3D content creation, encompassing both AI-powered methods and traditional workflows, is driving an unprecedented demand for automated rigging solutions that can keep pace with the increasing complexity and diversity of 3D models. We introduce UniRig, a novel, unified framework for automatic skeletal rigging that leverages the power of large autoregressive models and a bone-point cross-attention mechanism to generate both high-quality skeletons and skinning weights. Unlike previous methods that struggle with complex or non-standard topologies, UniRig accurately predicts topologically valid skeleton structures thanks to a new Skeleton Tree Tokenization method that efficiently encodes hierarchical relationships within the skeleton. To train and evaluate UniRig, we present Rig-XL, a new large-scale dataset of over 14,000 rigged 3D models spanning a wide range of categories. UniRig significantly outperforms state-of-the-art academic and commercial methods, achieving a 215% improvement in rigging accuracy and a 194% improvement in motion accuracy on challenging datasets. Our method works seamlessly across diverse object categories, from detailed anime characters to complex organic and inorganic structures, demonstrating its versatility and robustness. By automating the tedious and time-consuming rigging process, UniRig has the potential to speed up animation pipelines with unprecedented ease and efficiency. Project Page: https://zjp-shadow.github.io/works/UniRig/

First seen by Oriel on .

AI summary

UniRig is a unified automatic skeletal rigging framework that uses large autoregressive models to generate accurate skeletons and skinning weights across diverse 3D object categories.

  • A Skeleton Tree Tokenization method encodes hierarchical relationships, enabling prediction of topologically valid skeleton structures for complex and non-standard models.
  • Bone-point cross-attention supports generation of both skeletons and skinning weights.
  • Rig-XL provides more than 14,000 rigged 3D models across categories for training and evaluation.
  • UniRig reports 215% higher rigging accuracy and 194% higher motion accuracy than state-of-the-art academic and commercial methods on challenging datasets.
  • The framework handles detailed anime characters and complex organic and inorganic structures, aiming to reduce tedious manual work in animation pipelines.

#3d rigging #autoregressive models #computer animation #3d datasets

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 0, latest observation ; 0 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 0, latest observation ; 0 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2504.12451https://arxiv.org/abs/2504.12451 Read discussion