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

Bo Dai, Ziwei Liu, Chen Qian, Wayne Wu, Dahua Lin, Zhongang Cai, Lei Yang, Chen Wei, Shuai Liu, Zhaoxi Chen, Haiyi Mei, Zhitao Yang, and 3 more

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

• openxrlab/xrfeitoria — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Kong * Equal Contribution † Corresponding Author https://synbody.github.io/ Figure 1: SynBody is a large-scale synthetic dataset with a massive number of subjects and high-quality annotations. It supports various research topics, including human pose and shape estimation (HPS) and novel view synthesis for human (Human NeRF).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.17368")
get_code_for_paper("2303.17368")
have("2303.17368")

Connect an agent — have() is free.