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).
Project page: SynBody
Paper is released at arxiv
Codes & details will be released soon.
@InProceedings{yang2023synbody,
author = {Yang, Zhitao and Cai, Zhongang and Mei, Haiyi and Liu, Shuai and Chen, Zhaoxi and Xiao, Weiye and Wei, Yukun and Qing, Zhongfei and Wei, Chen and Dai, Bo and Wu, Wayne and Qian, Chen and Lin, Dahua and Liu, Ziwei and Yang, Lei},
title = {SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2023},
pages = {20282-20292}
}⭐ This project is powered by XRFeitoria (OpenXRLab Synthetic Data Rendering Toolbox).