Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On
We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, rep...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2020-09 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Vidaurre, Raquel Santesteban, Igor Garces, Elena Casas, Dan |
description | We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2441675336</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2441675336</sourcerecordid><originalsourceid>FETCH-proquest_journals_24416753363</originalsourceid><addsrcrecordid>eNqNjEELgjAYhkcQJOV_GHQWdJvaXdJO1kG6yohJ2tpn37bCf98O_YBOLw_Pw7siEeM8Sw6CsQ2JrZ3SNGVFyfKcR6SpvdYLrcC8QXs3gpGaNijnO22VxwCtch_Ah6UDIL1IlE_lcLzR64jOB9_hkpzNjqwHqa2Kf7sl-_rYVadkRnh5ZV0_gcdwbnsmRFaUOecF_6_6Ag7vO6w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2441675336</pqid></control><display><type>article</type><title>Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On</title><source>Free E- Journals</source><creator>Vidaurre, Raquel ; Santesteban, Igor ; Garces, Elena ; Casas, Dan</creator><creatorcontrib>Vidaurre, Raquel ; Santesteban, Igor ; Garces, Elena ; Casas, Dan</creatorcontrib><description>We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Decoupling ; Deformation mechanisms ; Finite element method ; Garments ; Graph neural networks ; Machine learning ; Network topologies ; Neural networks ; Topology optimization ; Virtual networks</subject><ispartof>arXiv.org, 2020-09</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Vidaurre, Raquel</creatorcontrib><creatorcontrib>Santesteban, Igor</creatorcontrib><creatorcontrib>Garces, Elena</creatorcontrib><creatorcontrib>Casas, Dan</creatorcontrib><title>Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On</title><title>arXiv.org</title><description>We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.</description><subject>Decoupling</subject><subject>Deformation mechanisms</subject><subject>Finite element method</subject><subject>Garments</subject><subject>Graph neural networks</subject><subject>Machine learning</subject><subject>Network topologies</subject><subject>Neural networks</subject><subject>Topology optimization</subject><subject>Virtual networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjEELgjAYhkcQJOV_GHQWdJvaXdJO1kG6yohJ2tpn37bCf98O_YBOLw_Pw7siEeM8Sw6CsQ2JrZ3SNGVFyfKcR6SpvdYLrcC8QXs3gpGaNijnO22VxwCtch_Ah6UDIL1IlE_lcLzR64jOB9_hkpzNjqwHqa2Kf7sl-_rYVadkRnh5ZV0_gcdwbnsmRFaUOecF_6_6Ag7vO6w</recordid><startdate>20200909</startdate><enddate>20200909</enddate><creator>Vidaurre, Raquel</creator><creator>Santesteban, Igor</creator><creator>Garces, Elena</creator><creator>Casas, Dan</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200909</creationdate><title>Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On</title><author>Vidaurre, Raquel ; Santesteban, Igor ; Garces, Elena ; Casas, Dan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24416753363</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Decoupling</topic><topic>Deformation mechanisms</topic><topic>Finite element method</topic><topic>Garments</topic><topic>Graph neural networks</topic><topic>Machine learning</topic><topic>Network topologies</topic><topic>Neural networks</topic><topic>Topology optimization</topic><topic>Virtual networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Vidaurre, Raquel</creatorcontrib><creatorcontrib>Santesteban, Igor</creatorcontrib><creatorcontrib>Garces, Elena</creatorcontrib><creatorcontrib>Casas, Dan</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Vidaurre, Raquel</au><au>Santesteban, Igor</au><au>Garces, Elena</au><au>Casas, Dan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On</atitle><jtitle>arXiv.org</jtitle><date>2020-09-09</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2020-09 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2441675336 |
source | Free E- Journals |
subjects | Decoupling Deformation mechanisms Finite element method Garments Graph neural networks Machine learning Network topologies Neural networks Topology optimization Virtual networks |
title | Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T08%3A58%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Fully%20Convolutional%20Graph%20Neural%20Networks%20for%20Parametric%20Virtual%20Try-On&rft.jtitle=arXiv.org&rft.au=Vidaurre,%20Raquel&rft.date=2020-09-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2441675336%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2441675336&rft_id=info:pmid/&rfr_iscdi=true |