Full body virtual try‐on with semi‐self‐supervised learning

Abstract This paper proposes a full body virtual try‐on which handles both top and bottom garments and generates realistic try‐on images. For the full body virtual try‐on, this paper addresses lack of suitable training data to align and fit top and bottom naturally. The proposed system consists of t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyug‐Jae Lee, Byumhyuk Koo, Ha‐Eun Ahn, Minseok Kang, Rokkyu Lee, Gunhan Park
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/1e9d778467f44d22a26f9f3182cabfcc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1e9d778467f44d22a26f9f3182cabfcc
record_format	dspace
spelling	oai:doaj.org-article:1e9d778467f44d22a26f9f3182cabfcc2021-11-19T05:42:53ZFull body virtual try‐on with semi‐self‐supervised learning1350-911X0013-519410.1049/ell2.12307https://doaj.org/article/1e9d778467f44d22a26f9f3182cabfcc2021-11-01T00:00:00Zhttps://doi.org/10.1049/ell2.12307https://doaj.org/toc/0013-5194https://doaj.org/toc/1350-911XAbstract This paper proposes a full body virtual try‐on which handles both top and bottom garments and generates realistic try‐on images. For the full body virtual try‐on, this paper addresses lack of suitable training data to align and fit top and bottom naturally. The proposed system consists of three modules: Clothing Guide Module (CGM), Geometric Matching Module (GMM), and Try‐On Module (TOM). CGM is introduced to generate a clothing guide map (CGMap) which describes the shape of a garment on a model. Unlike the single‐garment virtual try‐on scheme, it is impractical to collect meaningful data at a large scale for the multi‐garment system. To address this problem, two novel training strategies are proposed to leverage the existing training data. First, a pseudo triplet of model‐top‐bottom is generated from a pair of model‐top or model‐bottom which are already secured. Second, the CGM network is arranged to be exposed to both top and bottom garments during training. Then, the following GMM networks warp and align the top and bottom garments. Finally, TOM synthesizes a realistic try‐on image with the aligned garment and the CGMap. Experimental results prove remarkable performance of the proposed method in the full body virtual try‐on.Hyug‐Jae LeeByumhyuk KooHa‐Eun AhnMinseok KangRokkyu LeeGunhan ParkWileyarticleElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENElectronics Letters, Vol 57, Iss 24, Pp 915-917 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electrical engineering. Electronics. Nuclear engineering TK1-9971 Hyug‐Jae Lee Byumhyuk Koo Ha‐Eun Ahn Minseok Kang Rokkyu Lee Gunhan Park Full body virtual try‐on with semi‐self‐supervised learning
description	Abstract This paper proposes a full body virtual try‐on which handles both top and bottom garments and generates realistic try‐on images. For the full body virtual try‐on, this paper addresses lack of suitable training data to align and fit top and bottom naturally. The proposed system consists of three modules: Clothing Guide Module (CGM), Geometric Matching Module (GMM), and Try‐On Module (TOM). CGM is introduced to generate a clothing guide map (CGMap) which describes the shape of a garment on a model. Unlike the single‐garment virtual try‐on scheme, it is impractical to collect meaningful data at a large scale for the multi‐garment system. To address this problem, two novel training strategies are proposed to leverage the existing training data. First, a pseudo triplet of model‐top‐bottom is generated from a pair of model‐top or model‐bottom which are already secured. Second, the CGM network is arranged to be exposed to both top and bottom garments during training. Then, the following GMM networks warp and align the top and bottom garments. Finally, TOM synthesizes a realistic try‐on image with the aligned garment and the CGMap. Experimental results prove remarkable performance of the proposed method in the full body virtual try‐on.
format	article
author	Hyug‐Jae Lee Byumhyuk Koo Ha‐Eun Ahn Minseok Kang Rokkyu Lee Gunhan Park
author_facet	Hyug‐Jae Lee Byumhyuk Koo Ha‐Eun Ahn Minseok Kang Rokkyu Lee Gunhan Park
author_sort	Hyug‐Jae Lee
title	Full body virtual try‐on with semi‐self‐supervised learning
title_short	Full body virtual try‐on with semi‐self‐supervised learning
title_full	Full body virtual try‐on with semi‐self‐supervised learning
title_fullStr	Full body virtual try‐on with semi‐self‐supervised learning
title_full_unstemmed	Full body virtual try‐on with semi‐self‐supervised learning
title_sort	full body virtual try‐on with semi‐self‐supervised learning
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/1e9d778467f44d22a26f9f3182cabfcc
work_keys_str_mv	AT hyugjaelee fullbodyvirtualtryonwithsemiselfsupervisedlearning AT byumhyukkoo fullbodyvirtualtryonwithsemiselfsupervisedlearning AT haeunahn fullbodyvirtualtryonwithsemiselfsupervisedlearning AT minseokkang fullbodyvirtualtryonwithsemiselfsupervisedlearning AT rokkyulee fullbodyvirtualtryonwithsemiselfsupervisedlearning AT gunhanpark fullbodyvirtualtryonwithsemiselfsupervisedlearning
_version_	1718420362739318784

Full body virtual try‐on with semi‐self‐supervised learning

Ejemplares similares