BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuanpu, Song, Dan, Zhan, Pengxin, Chang, Tianyu, Zeng, Jianhao, Chen, Qingguo, Luo, Weihua, Liu, Anan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915030459482112
author Zhang, Xuanpu
Song, Dan
Zhan, Pengxin
Chang, Tianyu
Zeng, Jianhao
Chen, Qingguo
Luo, Weihua
Liu, Anan
author_facet Zhang, Xuanpu
Song, Dan
Zhan, Pengxin
Chang, Tianyu
Zeng, Jianhao
Chen, Qingguo
Luo, Weihua
Liu, Anan
contents Image-based virtual try-on is an increasingly popular and important task to generate realistic try-on images of the specific person. Recent methods model virtual try-on as image mask-inpaint task, which requires masking the person image and results in significant loss of spatial information. Especially, for in-the-wild try-on scenarios with complex poses and occlusions, mask-based methods often introduce noticeable artifacts. Our research found that a mask-free approach can fully leverage spatial and lighting information from the original person image, enabling high-quality virtual try-on. Consequently, we propose a novel training paradigm for a mask-free try-on diffusion model. We ensure the model's mask-free try-on capability by creating high-quality pseudo-data and further enhance its handling of complex spatial information through effective in-the-wild data augmentation. Besides, a try-on localization loss is designed to concentrate on try-on area while suppressing garment features in non-try-on areas, ensuring precise rendering of garments and preservation of fore/back-ground. In the end, we introduce BooW-VTON, the mask-free virtual try-on diffusion model, which delivers SOTA try-on quality without parsing cost. Extensive qualitative and quantitative experiments have demonstrated superior performance in wild scenarios with such a low-demand input.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06047
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
Zhang, Xuanpu
Song, Dan
Zhan, Pengxin
Chang, Tianyu
Zeng, Jianhao
Chen, Qingguo
Luo, Weihua
Liu, Anan
Computer Vision and Pattern Recognition
Image-based virtual try-on is an increasingly popular and important task to generate realistic try-on images of the specific person. Recent methods model virtual try-on as image mask-inpaint task, which requires masking the person image and results in significant loss of spatial information. Especially, for in-the-wild try-on scenarios with complex poses and occlusions, mask-based methods often introduce noticeable artifacts. Our research found that a mask-free approach can fully leverage spatial and lighting information from the original person image, enabling high-quality virtual try-on. Consequently, we propose a novel training paradigm for a mask-free try-on diffusion model. We ensure the model's mask-free try-on capability by creating high-quality pseudo-data and further enhance its handling of complex spatial information through effective in-the-wild data augmentation. Besides, a try-on localization loss is designed to concentrate on try-on area while suppressing garment features in non-try-on areas, ensuring precise rendering of garments and preservation of fore/back-ground. In the end, we introduce BooW-VTON, the mask-free virtual try-on diffusion model, which delivers SOTA try-on quality without parsing cost. Extensive qualitative and quantitative experiments have demonstrated superior performance in wild scenarios with such a low-demand input.
title BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.06047