Enhanced Realism in Virtual Try-On Tasks Using Diffusion Methods

Virtual try-on technology is revolutionizing online retail by enabling customers to visualize garments on their bodies before purchasing. Traditional methods, often based on Generative Adversarial Networks (GANs), face challenges such as misalignment and visual artifacts, especially in complex poses...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2025 11th International Conference on Computing and Artificial Intelligence (ICCAI) S. 128 - 133
Hauptverfasser: Kiattithapanayong, Saris, Phoomvuthisarn, Suronapee
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 28.03.2025
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Virtual try-on technology is revolutionizing online retail by enabling customers to visualize garments on their bodies before purchasing. Traditional methods, often based on Generative Adversarial Networks (GANs), face challenges such as misalignment and visual artifacts, especially in complex poses. We present a virtual try-on framework leveraging diffusion models to enhance realism, accuracy, and garment detail preservation. Our approach integrates Vector Quantized Variational Autoencoders (VQ-VAEs) for precise feature matching within a diffusion U-Net architecture. By adopting image-based conditioning with the CLIP image encoder, our system utilizes visual features directly from clothing images for more faithful garment representations. Additionally, an Additional Feature Preserving Block (ControlNet) maintains intricate details like textures and logos, addressing fine-grained garment fidelity challenges. Quantitative evaluation demonstrates our system's superior performance, achieving the best LPIPS of 0.082. We also achieve a Fréchet Inception Distance (FID) of 7.782 and Kernel Inception Distance (KID) of 1.53, indicating enhanced image quality and feature alignment. Although the Structural Similarity Index Measure (SSIM) of \mathbf{0. 8 2 5} is slightly lower, it underscores the trade-off for improved realism and garment detail preservation. Our contributions set a new benchmark for accurate and realistic clothing visualization in virtual try-on systems.
AbstractList Virtual try-on technology is revolutionizing online retail by enabling customers to visualize garments on their bodies before purchasing. Traditional methods, often based on Generative Adversarial Networks (GANs), face challenges such as misalignment and visual artifacts, especially in complex poses. We present a virtual try-on framework leveraging diffusion models to enhance realism, accuracy, and garment detail preservation. Our approach integrates Vector Quantized Variational Autoencoders (VQ-VAEs) for precise feature matching within a diffusion U-Net architecture. By adopting image-based conditioning with the CLIP image encoder, our system utilizes visual features directly from clothing images for more faithful garment representations. Additionally, an Additional Feature Preserving Block (ControlNet) maintains intricate details like textures and logos, addressing fine-grained garment fidelity challenges. Quantitative evaluation demonstrates our system's superior performance, achieving the best LPIPS of 0.082. We also achieve a Fréchet Inception Distance (FID) of 7.782 and Kernel Inception Distance (KID) of 1.53, indicating enhanced image quality and feature alignment. Although the Structural Similarity Index Measure (SSIM) of \mathbf{0. 8 2 5} is slightly lower, it underscores the trade-off for improved realism and garment detail preservation. Our contributions set a new benchmark for accurate and realistic clothing visualization in virtual try-on systems.
Author Phoomvuthisarn, Suronapee
Kiattithapanayong, Saris
Author_xml – sequence: 1
  givenname: Saris
  surname: Kiattithapanayong
  fullname: Kiattithapanayong, Saris
  email: saris.kiat@gmail.com
  organization: Chulalongkorn University,Faculty of Commerce and Accountancy,Department of Statistics,Bangkok,Thailand
– sequence: 2
  givenname: Suronapee
  surname: Phoomvuthisarn
  fullname: Phoomvuthisarn, Suronapee
  email: suronapee@cbs.chula.ac.th
  organization: Chulalongkorn University,Faculty of Commerce and Accountancy,Department of Statistics,Bangkok,Thailand
BookMark eNotjctOwzAUBY0ECyj9A5D8Awm-ftXeUYVSIhVVagPbyvGDWqQOitNF_55IcDazGc25Q9epTx6hRyAlANFPdVUtaykFgZISKkpCCFVXaK4XWjEGgnIN7BY9r9LRJOsd3nnTxXzCMeHPOIxn0-FmuBTbhBuTvzP-yDF94ZcYwjnHPuF3Px57l-_RTTBd9vN_ztD-ddVUb8Vmu66r5aaImo0F59pOz5RAa62kllhwLSzA0sCZY9JJJ5iDaSJQzYxWXFCvnW6d8kaxGXr4q0bv_eFniCczXA6TToTikv0C2jlGCw
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCAI66501.2025.00028
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331524913
EndPage 133
ExternalDocumentID 11105846
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-449c979201bcc62c0c1db171c2f43d36d6d53d11115f293a98452e9d9bd8ea83
IEDL.DBID RIE
IngestDate Wed Aug 20 06:20:56 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-449c979201bcc62c0c1db171c2f43d36d6d53d11115f293a98452e9d9bd8ea83
PageCount 6
ParticipantIDs ieee_primary_11105846
PublicationCentury 2000
PublicationDate 2025-March-28
PublicationDateYYYYMMDD 2025-03-28
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-March-28
  day: 28
PublicationDecade 2020
PublicationTitle 2025 11th International Conference on Computing and Artificial Intelligence (ICCAI)
PublicationTitleAbbrev ICCAI
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9034373
Snippet Virtual try-on technology is revolutionizing online retail by enabling customers to visualize garments on their bodies before purchasing. Traditional methods,...
SourceID ieee
SourceType Publisher
StartPage 128
SubjectTerms Accuracy
Autoencoders
Benchmark testing
Computer architecture
ControlNet
Diffusion models
Diffusions
Kernel
Training
Vectors
Virtual Tryon
Visualization
Title Enhanced Realism in Virtual Try-On Tasks Using Diffusion Methods
URI https://ieeexplore.ieee.org/document/11105846
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62ePCkYsU3OXiN3Tw2j5tSW-zBWrRIb2U3yeIibstuK_jvzaT1cfHgLQSSkITMl0zmmw-hS8dEIY1yhGaaE6G8IFmSU2JTkbFC62A4RRSbUKORnk7NeENWj1wY730MPvNXUIx_-W5uV-Aq64ZzmQBgtlBLKbkma21YOTQx3WGvdzOU4coB7z4GvpIERNZ_qaZE0Bjs_nO4PdT5od_h8Tew7KMtXx2g6371En_r8aOHpIVvuKzwc1kD_wNP6g_yUOFJ1rw2OEYB4NuyKFbgCsP3USS66aCnQX_SuyMb-QNSGr4kQhhrlAkAnVsrmU0sdTlV1LJCcMelky7lDixeWgTMzowWKfPGmdxpHxb-ELWreeWPEA52BBizlMqYPU6bJPSa83B54rkKrY5RByY_W6zzW8y-5n3yR_0p2oH1hUgsps9Qe1mv_Dnatu_Lsqkv4q58AtG7jEw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA86BT2pOPHbHLzGNR9tk5syNxxuc2iR3UabpFjETtpN8L83L9aPiwdvIZCEJOT9kpf3ez-Ezg0TeaRiQ2gqORGxFSQNMkp0KFKWS-kMp_BiE_F4LKdTNWnI6p4LY631wWf2Aor-L9_M9RJcZR13LgMAzFW0BtJZDV2r4eXQQHUG3e7VIHKXDnj5MfCWBCCz_ks3xcNGf-ufA26j9g8BD0--oWUHrdhyF132yif_X4_vLaQtfMFFiR-LChggOKneyV2Jk7R-rrGPA8DXRZ4vwRmGR14mum6jh34v6d6QRgCBFIoviBBKq1g5iM60jpgONDUZjalmueCGRyYyITdg88LcoXaqpAiZVUZlRlq39HuoVc5Lu4-wsyTAmaU08vnjpApcrxl31yeexa7VAWrD5GevnxkuZl_zPvyj_gxt3CSj4Ww4GN8eoU1Ya4jLYvIYtRbV0p6gdf22KOrq1O_QB1X6j5U
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+11th+International+Conference+on+Computing+and+Artificial+Intelligence+%28ICCAI%29&rft.atitle=Enhanced+Realism+in+Virtual+Try-On+Tasks+Using+Diffusion+Methods&rft.au=Kiattithapanayong%2C+Saris&rft.au=Phoomvuthisarn%2C+Suronapee&rft.date=2025-03-28&rft.pub=IEEE&rft.spage=128&rft.epage=133&rft_id=info:doi/10.1109%2FICCAI66501.2025.00028&rft.externalDocID=11105846