CLOTH3D: Clothed 3D Humans

Abstract

We present CLOTH3D, the first big scale synthetic dataset of 3D clothed human sequences. CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. We provide the dataset with a generative model for cloth generation. We propose a Conditional Variational Auto-Encoder (CVAE) based on graph convolutions (GCVAE) to learn garment latent spaces. This allows for realistic generation of 3D garments on top of SMPL model for any pose and shape.

Cite

Text

Bertiche et al. "CLOTH3D: Clothed 3D Humans." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58565-5_21

Markdown

[Bertiche et al. "CLOTH3D: Clothed 3D Humans." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/bertiche2020eccv-cloth3d/) doi:10.1007/978-3-030-58565-5_21

BibTeX

@inproceedings{bertiche2020eccv-cloth3d,
  title     = {{CLOTH3D: Clothed 3D Humans}},
  author    = {Bertiche, Hugo and Madadi, Meysam and Escalera, Sergio},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58565-5_21},
  url       = {https://mlanthology.org/eccv/2020/bertiche2020eccv-cloth3d/}
}