HumanRig:
Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset

AMAP, Alibaba

HumanRig deals well with both AI and manual generated humanoid meshes, especially for those with complex clothes or accessories and irregular body shapes.

Abstract

With the rapid evolution of 3D generation algorithms, the cost of producing 3D humanoid character models has plummeted, yet the field is impeded by the lack of a comprehensive dataset for automatic rigging—a pivotal step in character animation. Addressing this gap, we present HumanRig, the first large-scale dataset specifically designed for 3D humanoid character rigging, encompassing 11,434 meticulously curated T-posed meshes adhered to a uniform skeleton topology. Capitalizing on this dataset, we introduce an innovative, data-driven automatic rigging framework, which overcomes the limitations of GNN-based methods in handling complex AI-generated meshes. Our approach integrates a Prior-Guided Skeleton Estimator (PGSE) module, which uses 2D skeleton joints to provide a preliminary 3D skeleton, and a Mesh-Skeleton Mutual Attention Network (MSMAN) that fuses skeleton features with 3D mesh features extracted by a U-shaped point transformer. This enables a coarse-to-fine 3D skeleton joint regression and a robust skinning estimation, surpassing previous methods in quality and versatility. This work not only remedies the dataset deficiency in rigging research but also propels the animation industry towards more efficient and automated character rigging pipelines.

Video

Auto rigging framework

Method Overview. Given a humanoid mesh, a coarse skeleton is predicted by an Prior-guided skeleton estimator (PGSE) and helps construct the skeleton-aware vertex features. They are fed into Skeleton Encoder and Mesh Encoder, respectively, then fused by a Mesh-Skeleton Mutual Attention Network to predict a refined skeleton and skinning weights with a joint learning strategy. Finally, the skeleton and skinning weights are combined to produce the animation-ready character.

HumanRig Dataset

Existing datasets are limited in quantity, diversity or skeleton unity. Our dataset bridges these gaps by offering a large-scale collection of 11,434 AI-generated meshes with diverse head-to-body ratios, aligned with a consistent Mixamo skeleton, thereby enhancing both the quantity and diversity of available models for rigging research and applications.

Skeleton Construction Comparison

Skinning and Deformation Comparison

BibTeX


      @misc{chu2024humanriglearningautomaticrigging,
      title={HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset}, 
      author={Zedong Chu and Feng Xiong and Meiduo Liu and Jinzhi Zhang and Mingqi Shao and Zhaoxu Sun and Di Wang and Mu Xu},
      year={2024},
      eprint={2412.02317},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.02317}, 
}