Try-On-Adapter: A Simple and Flexible Try-On Paradigm

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Hanzhong, Zhang, Jianfeng, Zou, Cheng, Li, Jun, Wang, Meng, Wen, Ruxue, Tang, Pingzhong, Chen, Jingdong, Yang, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915022096039936
author Guo, Hanzhong
Zhang, Jianfeng
Zou, Cheng
Li, Jun
Wang, Meng
Wen, Ruxue
Tang, Pingzhong
Chen, Jingdong
Yang, Ming
author_facet Guo, Hanzhong
Zhang, Jianfeng
Zou, Cheng
Li, Jun
Wang, Meng
Wen, Ruxue
Tang, Pingzhong
Chen, Jingdong
Yang, Ming
contents Image-based virtual try-on, widely used in online shopping, aims to generate images of a naturally dressed person conditioned on certain garments, providing significant research and commercial potential. A key challenge of try-on is to generate realistic images of the model wearing the garments while preserving the details of the garments. Previous methods focus on masking certain parts of the original model's standing image, and then inpainting on masked areas to generate realistic images of the model wearing corresponding reference garments, which treat the try-on task as an inpainting task. However, such implements require the user to provide a complete, high-quality standing image, which is user-unfriendly in practical applications. In this paper, we propose Try-On-Adapter (TOA), an outpainting paradigm that differs from the existing inpainting paradigm. Our TOA can preserve the given face and garment, naturally imagine the rest parts of the image, and provide flexible control ability with various conditions, e.g., garment properties and human pose. In the experiments, TOA shows excellent performance on the virtual try-on task even given relatively low-quality face and garment images in qualitative comparisons. Additionally, TOA achieves the state-of-the-art performance of FID scores 5.56 and 7.23 for paired and unpaired on the VITON-HD dataset in quantitative comparisons.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10187
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Try-On-Adapter: A Simple and Flexible Try-On Paradigm
Guo, Hanzhong
Zhang, Jianfeng
Zou, Cheng
Li, Jun
Wang, Meng
Wen, Ruxue
Tang, Pingzhong
Chen, Jingdong
Yang, Ming
Computer Vision and Pattern Recognition
Image-based virtual try-on, widely used in online shopping, aims to generate images of a naturally dressed person conditioned on certain garments, providing significant research and commercial potential. A key challenge of try-on is to generate realistic images of the model wearing the garments while preserving the details of the garments. Previous methods focus on masking certain parts of the original model's standing image, and then inpainting on masked areas to generate realistic images of the model wearing corresponding reference garments, which treat the try-on task as an inpainting task. However, such implements require the user to provide a complete, high-quality standing image, which is user-unfriendly in practical applications. In this paper, we propose Try-On-Adapter (TOA), an outpainting paradigm that differs from the existing inpainting paradigm. Our TOA can preserve the given face and garment, naturally imagine the rest parts of the image, and provide flexible control ability with various conditions, e.g., garment properties and human pose. In the experiments, TOA shows excellent performance on the virtual try-on task even given relatively low-quality face and garment images in qualitative comparisons. Additionally, TOA achieves the state-of-the-art performance of FID scores 5.56 and 7.23 for paired and unpaired on the VITON-HD dataset in quantitative comparisons.
title Try-On-Adapter: A Simple and Flexible Try-On Paradigm
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.10187