Garment Recovery with Shape and Deformation Priors

Abstract

While modeling people wearing tight-fitting clothing has made great strides in recent years loose-fitting clothing remains a challenge. We propose a method that delivers realistic garment models from real-world images regardless of garment shape or deformation. To this end we introduce a fitting approach that utilizes shape and deformation priors learned from synthetic data to accurately capture garment shapes and deformations including large ones. Not only does our approach recover the garment geometry accurately it also yields models that can be directly used by downstream applications such as animation and simulation.

Cite

Text

Li et al. "Garment Recovery with Shape and Deformation Priors." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.00157

Markdown

[Li et al. "Garment Recovery with Shape and Deformation Priors." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/li2024cvpr-garment/) doi:10.1109/CVPR52733.2024.00157

BibTeX

@inproceedings{li2024cvpr-garment,
  title     = {{Garment Recovery with Shape and Deformation Priors}},
  author    = {Li, Ren and Dumery, Corentin and Guillard, Benoît and Fua, Pascal},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2024},
  pages     = {1586-1595},
  doi       = {10.1109/CVPR52733.2024.00157},
  url       = {https://mlanthology.org/cvpr/2024/li2024cvpr-garment/}
}