Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Luyang, Li, Yingwei, Liu, Nan, Peng, Hao, Yang, Dawei, Kemelmacher-Shlizerman, Ira
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2406.04542
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917687408459776
author Zhu, Luyang
Li, Yingwei
Liu, Nan
Peng, Hao
Yang, Dawei
Kemelmacher-Shlizerman, Ira
author_facet Zhu, Luyang
Li, Yingwei
Liu, Nan
Peng, Hao
Yang, Dawei
Kemelmacher-Shlizerman, Ira
contents We present M&M VTO, a mix and match virtual try-on method that takes as input multiple garment images, text description for garment layout and an image of a person. An example input includes: an image of a shirt, an image of a pair of pants, "rolled sleeves, shirt tucked in", and an image of a person. The output is a visualization of how those garments (in the desired layout) would look like on the given person. Key contributions of our method are: 1) a single stage diffusion based model, with no super resolution cascading, that allows to mix and match multiple garments at 1024x512 resolution preserving and warping intricate garment details, 2) architecture design (VTO UNet Diffusion Transformer) to disentangle denoising from person specific features, allowing for a highly effective finetuning strategy for identity preservation (6MB model per individual vs 4GB achieved with, e.g., dreambooth finetuning); solving a common identity loss problem in current virtual try-on methods, 3) layout control for multiple garments via text inputs specifically finetuned over PaLI-3 for virtual try-on task. Experimental results indicate that M&M VTO achieves state-of-the-art performance both qualitatively and quantitatively, as well as opens up new opportunities for virtual try-on via language-guided and multi-garment try-on.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04542
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M&M VTO: Multi-Garment Virtual Try-On and Editing
Zhu, Luyang
Li, Yingwei
Liu, Nan
Peng, Hao
Yang, Dawei
Kemelmacher-Shlizerman, Ira
Computer Vision and Pattern Recognition
Graphics
We present M&M VTO, a mix and match virtual try-on method that takes as input multiple garment images, text description for garment layout and an image of a person. An example input includes: an image of a shirt, an image of a pair of pants, "rolled sleeves, shirt tucked in", and an image of a person. The output is a visualization of how those garments (in the desired layout) would look like on the given person. Key contributions of our method are: 1) a single stage diffusion based model, with no super resolution cascading, that allows to mix and match multiple garments at 1024x512 resolution preserving and warping intricate garment details, 2) architecture design (VTO UNet Diffusion Transformer) to disentangle denoising from person specific features, allowing for a highly effective finetuning strategy for identity preservation (6MB model per individual vs 4GB achieved with, e.g., dreambooth finetuning); solving a common identity loss problem in current virtual try-on methods, 3) layout control for multiple garments via text inputs specifically finetuned over PaLI-3 for virtual try-on task. Experimental results indicate that M&M VTO achieves state-of-the-art performance both qualitatively and quantitatively, as well as opens up new opportunities for virtual try-on via language-guided and multi-garment try-on.
title M&M VTO: Multi-Garment Virtual Try-On and Editing
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2406.04542