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 straight-forward generation impedes 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. To this end, 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.

arXiv commentAccepted by CVPR2021

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Unsupervised Cross-Domain Image Generation
• Detailed Garment Recovery from a Single-View Image
• Learning to Synthesize Fashion Textures