OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Ke, Cao, Jian, Wang, Qi, Tian, Linrui, Zhang, Xindi, Zhuo, Lian, Zhang, Bang, Bo, Liefeng, Zhou, Wenbo, Zhang, Weiming, Gao, Daiheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916333149487104
author Sun, Ke
Cao, Jian
Wang, Qi
Tian, Linrui
Zhang, Xindi
Zhuo, Lian
Zhang, Bang
Bo, Liefeng
Zhou, Wenbo
Zhang, Weiming
Gao, Daiheng
author_facet Sun, Ke
Cao, Jian
Wang, Qi
Tian, Linrui
Zhang, Xindi
Zhuo, Lian
Zhang, Bang
Bo, Liefeng
Zhou, Wenbo
Zhang, Weiming
Gao, Daiheng
contents Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent results. While diffusion models, such as Stable Diffusion series, have shown their capability in creating high-quality and photorealistic images, they encounter formidable challenges in conditional generation scenarios like VTON. Specifically, these models struggle to maintain a balance between control and consistency when generating images for virtual clothing trials. OutfitAnyone addresses these limitations by leveraging a two-stream conditional diffusion model, enabling it to adeptly handle garment deformation for more lifelike results. It distinguishes itself with scalability-modulating factors such as pose, body shape and broad applicability, extending from anime to in-the-wild images. OutfitAnyone's performance in diverse scenarios underscores its utility and readiness for real-world deployment. For more details and animated results, please see \url{https://humanaigc.github.io/outfit-anyone/}.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16224
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person
Sun, Ke
Cao, Jian
Wang, Qi
Tian, Linrui
Zhang, Xindi
Zhuo, Lian
Zhang, Bang
Bo, Liefeng
Zhou, Wenbo
Zhang, Weiming
Gao, Daiheng
Computer Vision and Pattern Recognition
Virtual Try-On (VTON) has become a transformative technology, empowering users to experiment with fashion without ever having to physically try on clothing. However, existing methods often struggle with generating high-fidelity and detail-consistent results. While diffusion models, such as Stable Diffusion series, have shown their capability in creating high-quality and photorealistic images, they encounter formidable challenges in conditional generation scenarios like VTON. Specifically, these models struggle to maintain a balance between control and consistency when generating images for virtual clothing trials. OutfitAnyone addresses these limitations by leveraging a two-stream conditional diffusion model, enabling it to adeptly handle garment deformation for more lifelike results. It distinguishes itself with scalability-modulating factors such as pose, body shape and broad applicability, extending from anime to in-the-wild images. OutfitAnyone's performance in diverse scenarios underscores its utility and readiness for real-world deployment. For more details and animated results, please see \url{https://humanaigc.github.io/outfit-anyone/}.
title OutfitAnyone: Ultra-high Quality Virtual Try-On for Any Clothing and Any Person
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.16224