Shape of You: Precise 3D Shape Estimations for Diverse Body Types
Abstract
This paper presents Shape of You (SoY), an approach to improve the accuracy of 3D body shape estimation for vision-based clothing recommendation systems. While existing methods have successfully estimated 3D poses, there remains a lack of work in precise shape estimation, particularly for diverse human bodies. To address this gap, we propose two loss functions that can be readily integrated into parametric 3D human reconstruction pipelines. Additionally, we propose a test-time optimization routine that further improves quality. Our method improves over the recent SHAPY [7] method by 17.7% on the challenging SSP-3D dataset [16]. We consider our work to be a step towards a more accurate 3D shape estimation system that works reliably on diverse body types and holds promise for practical applications in the fashion industry.
Cite
Text
Sarkar et al. "Shape of You: Precise 3D Shape Estimations for Diverse Body Types." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00357Markdown
[Sarkar et al. "Shape of You: Precise 3D Shape Estimations for Diverse Body Types." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/sarkar2023cvprw-shape/) doi:10.1109/CVPRW59228.2023.00357BibTeX
@inproceedings{sarkar2023cvprw-shape,
title = {{Shape of You: Precise 3D Shape Estimations for Diverse Body Types}},
author = {Sarkar, Rohan and Dave, Achal and Medioni, Gérard G. and Biggs, Benjamin},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2023},
pages = {3520-3524},
doi = {10.1109/CVPRW59228.2023.00357},
url = {https://mlanthology.org/cvprw/2023/sarkar2023cvprw-shape/}
}