-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Ge_2021_CVPR, author = {Ge, Chongjian and Song, Yibing and Ge, Yuying and Yang, Han and Liu, Wei and Luo, Ping}, title = {Disentangled Cycle Consistency for Highly-Realistic Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {16928-16937} }
Disentangled Cycle Consistency for Highly-Realistic Virtual Try-On
Abstract
Image virtual try-on replaces the clothes on a person image with a desired in-shop clothes image. It is challenging because the person and the in-shop clothes are unpaired. Existing methods formulate virtual try-on as either in-painting or cycle consistency. Both of these two formulations encourage the generation networks to reconstruct the input image in a self-supervised manner. However, existing methods do not differentiate clothing and non-clothing regions. A straightforward generation impedes the virtual try-on quality because of the heavily coupled image contents. In this paper, we propose a Disentangled Cycle-consistency Try-On Network (DCTON). The DCTON is able to produce highly-realistic try-on images by disentangling important components of virtual try-on including clothes warping, skin synthesis, and image composition. Moreover, DCTON can be naturally trained in a self-supervised manner following cycle consistency learning. Extensive experiments on challenging benchmarks show that DCTON outperforms state-of-the-art approaches favorably.
Related Material