Learning to Wear: Details-Preserved Virtual Try-on via Disentangling Clothes and Wearer
Sangho Lee (Seoul National University), Seo Young Lee (Seoul National University), Joonseok Lee (Google Research & Seoul National University)*
The 33rd British Machine Vision Conference
Abstract
Virtual try-on, fitting an image of a garment to an image of a person, has rapidly progressed recently. However, existing virtual try-on methods still struggle to faithfully represent various details of the clothes when worn. In this paper, we propose a simple yet effective method to better preserve details of the clothing and person by introducing an additional fitting step after geometric warping. This minimal modification helps to effectively learn disentangled representations of the clothing from the wearer. By disentangling these two major components for virtual try-on, we are able to preserve the wearer-agnostic structure and details of the clothing, and thus can fit a garment naturally to a variety of poses and body shapes. Moreover, we propose a novel evaluation framework applicable to any metric, to better reflect the semantics of clothes fitting. From extensive experiments, we empirically verify that the proposed method not only learns to disentangle clothing from the wearer, but also preserves details of the clothing on the try-on results.Video
Citation
@inproceedings{Lee_2022_BMVC,
author = {Sangho Lee and Seo Young Lee and Joonseok Lee},
title = {Learning to Wear: Details-Preserved Virtual Try-on via Disentangling Clothes and Wearer},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0272.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by