File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV51070.2023.01855
- Scopus: eid_2-s2.0-85185338766
- Find via
Supplementary
-
Citations:
- Scopus: 7
- Appears in Collections:
Conference Paper: SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
Title | SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling |
---|---|
Authors | |
Issue Date | 2023 |
Citation | Proceedings of the IEEE International Conference on Computer Vision, 2023, p. 20225-20235 How to Cite? |
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 1.2M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1,187 actions, and various viewpoints. The dataset includes two subsets for human pose and shape estimation 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). |
Persistent Identifier | http://hdl.handle.net/10722/352408 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Zhitao | - |
dc.contributor.author | Cai, Zhongang | - |
dc.contributor.author | Mei, Haiyi | - |
dc.contributor.author | Liu, Shuai | - |
dc.contributor.author | Chen, Zhaoxi | - |
dc.contributor.author | Xiao, Weiye | - |
dc.contributor.author | Wei, Yukun | - |
dc.contributor.author | Qing, Zhongfei | - |
dc.contributor.author | Wei, Chen | - |
dc.contributor.author | Dai, Bo | - |
dc.contributor.author | Wu, Wayne | - |
dc.contributor.author | Qian, Chen | - |
dc.contributor.author | Lin, Dahua | - |
dc.contributor.author | Liu, Ziwei | - |
dc.contributor.author | Yang, Lei | - |
dc.date.accessioned | 2024-12-16T03:58:46Z | - |
dc.date.available | 2024-12-16T03:58:46Z | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | Proceedings of the IEEE International Conference on Computer Vision, 2023, p. 20225-20235 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/352408 | - |
dc.description.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 1.2M images with corresponding accurate 3D annotations, covering 10,000 human body models, 1,187 actions, and various viewpoints. The dataset includes two subsets for human pose and shape estimation 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). | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE International Conference on Computer Vision | - |
dc.title | SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV51070.2023.01855 | - |
dc.identifier.scopus | eid_2-s2.0-85185338766 | - |
dc.identifier.spage | 20225 | - |
dc.identifier.epage | 20235 | - |