SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

Zhitao Yang1,*     Zhongang Cai1,2,*     Haiyi Mei1,*     Shuai Liu2,*      Zhaoxi Chen3,*
Weiye Xiao1     Yukun Wei1     Zhongfei Qing1     Chen Wei1
Bo Dai2     Wayne Wu1,2     Chen Qian1     Dahua Lin2,4     Ziwei Liu3,✉     Lei Yang1,2,✉
1SenseTime Research      2Shanghai AI Laboratory
3S-Lab, Nanyang Technological University      4The Chinese University of Hong Kong
*Equal Contribution    Corresponding Author
teaser

SynBody is a large-scale synthetic dataset with massive number of subjects and high-quality annotations. It supports various research topics, including human mesh recovery and novel view synthesis for human (Human NeRF).

Abstract

Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets. To advance the diversity and annotation quality of human models, we introduce a new synthetic dataset, Synbody, with three appealing features: 1) a clothed parametric human model that can generate a diverse range of subjects; 2) the layered human representation that naturally offers high-quality 3D annotations to support multiple tasks; 3) a scalable system for producing realistic data to facilitate real-world tasks. The dataset comprises 1.7M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1000 actions, and various viewpoints. The dataset includes two subsets for human mesh recovery as well as human neural rendering. Extensive experiments on SynBody indicate that it substantially enhances both SMPL and SMPL-X estimation. Furthermore, the incorporation of layered annotations offers a valuable training resource for investigating the Human Neural Radiance Fields (NeRF).

Video

Updates



Register for future updates!

BibTeX

@misc{yang2023synbody,
  title={SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling}, 
  author={Zhitao, Yang and Zhongang, Cai and Haiyi, Mei and Shuai, Liu and Zhaoxi, Chen and Weiye, Xiao and Yukun, Wei and Zhongfei, Qing and Chen, Wei and Bo, Dai and Wayne, Wu and Chen, Qian and Dahua, Lin and Ziwei, Liu and Lei, Yang},
  year={2023},
  journal={arXiv preprint arXiv:2303.17368},
}