Optimization of Graph Convolutional Networks with Variational Graph Autoencoder Architecture for 3D Face Reconstruction Task

The study addresses the fundamental challenges encountered in 3D face reconstruction, including the inadequacy of dedicated research initiatives, the complexity of hyperparameter optimization, the lack of accessible guidance for newcomers, and the dependency on low-quality datasets. To surmount thes...

Full description

Saved in:
Bibliographic Details
Published in:Intelligent Systems and Computer Vision (Online) pp. 1 - 8
Main Authors: Batarfi, Mahfoudh M., Mareboyana, Manohar
Format: Conference Proceeding
Language:English
Published: IEEE 08.05.2024
Subjects:
ISSN:2768-0754
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The study addresses the fundamental challenges encountered in 3D face reconstruction, including the inadequacy of dedicated research initiatives, the complexity of hyperparameter optimization, the lack of accessible guidance for newcomers, and the dependency on low-quality datasets. To surmount these obstacles, the study embarks on the optimization of a Variational Graph Autoencoder (VGAE)-based architecture enriched with five distinct Graph Convolutional Network (GCN) layers, namely GCNConv, SGConv, SSGConv, GraphConv, and Chebyshev. The primary objective is twofold: first, to curate a diverse and high-fidelity 3D face dataset capable of meeting the criteria of this study posed by large-scale data intricacies, and second, to refine VGAE architectures through the strategic integration of these GCN layers. This integration aims to bolster the reconstruction capabilities of VGAE architectures and ascertain the optimal GCN layer type for maximizing accuracy (by minimizing validation loss) and computational efficiency (measured in execution time). Furthermore, the study provides comprehensive guidance tailored for researchers navigating the complexities of 3D face reconstruction. Through these concerted efforts, the findings of this research empower researchers to tackle challenging tasks such as facial analysis and reconstruction across various domains. The study endeavors to propel the field of 3D face reconstruction forward, offering valuable insights and methodologies to enhance the efficacy of VGAE architectures across diverse applications and domains. Moreover, the techniques and knowledge derived from this study can contribute to developing robust and efficient approaches for Generative AI applications beyond 3D face mesh reconstruction.
AbstractList The study addresses the fundamental challenges encountered in 3D face reconstruction, including the inadequacy of dedicated research initiatives, the complexity of hyperparameter optimization, the lack of accessible guidance for newcomers, and the dependency on low-quality datasets. To surmount these obstacles, the study embarks on the optimization of a Variational Graph Autoencoder (VGAE)-based architecture enriched with five distinct Graph Convolutional Network (GCN) layers, namely GCNConv, SGConv, SSGConv, GraphConv, and Chebyshev. The primary objective is twofold: first, to curate a diverse and high-fidelity 3D face dataset capable of meeting the criteria of this study posed by large-scale data intricacies, and second, to refine VGAE architectures through the strategic integration of these GCN layers. This integration aims to bolster the reconstruction capabilities of VGAE architectures and ascertain the optimal GCN layer type for maximizing accuracy (by minimizing validation loss) and computational efficiency (measured in execution time). Furthermore, the study provides comprehensive guidance tailored for researchers navigating the complexities of 3D face reconstruction. Through these concerted efforts, the findings of this research empower researchers to tackle challenging tasks such as facial analysis and reconstruction across various domains. The study endeavors to propel the field of 3D face reconstruction forward, offering valuable insights and methodologies to enhance the efficacy of VGAE architectures across diverse applications and domains. Moreover, the techniques and knowledge derived from this study can contribute to developing robust and efficient approaches for Generative AI applications beyond 3D face mesh reconstruction.
Author Batarfi, Mahfoudh M.
Mareboyana, Manohar
Author_xml – sequence: 1
  givenname: Mahfoudh M.
  surname: Batarfi
  fullname: Batarfi, Mahfoudh M.
  email: mbatarfi@bowiestate.edu
  organization: Bowie State University,Department Of Computer Science,Bowie,MD,USA
– sequence: 2
  givenname: Manohar
  surname: Mareboyana
  fullname: Mareboyana, Manohar
  email: mmareboyana@bowiestate.edu
  organization: Bowie State University,Department Of Computer Science,Bowie,MD,USA
BookMark eNo1UNtKAzEUjKJgrf0DwfzA1pNks9k8ltVWoVjQ0teSzYXGtpuSzVoUP95qKwzMMHM4A3ONLprQWITuCAwJAXn__FYtCuCEDinQfEigoEAKdoYGUsiScTiACHaOelQUZQaC51do0LbvAMAo5IRCD33Pdslv_ZdKPjQ4ODyJarfCVWg-wqb7NdUGv9i0D3Hd4r1PK7xQ0atTcrwedSnYRgdjIx5FvfLJ6tRFi12ImD3gsdIWv1odmjbFTv9VzVW7vkGXTm1aOzhxH83Hj_PqKZvOJs_VaJp5SVKmSC5Lx0DWNRGGOwPiIBnVQgDT0qqCq5qVrgbglJJSFdRoZ4xypNSGctZHt8e33lq73EW_VfFz-b8X-wEUa2Qg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ISCV60512.2024.10620163
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 9798350350173
9798350350180
EISSN 2768-0754
EndPage 8
ExternalDocumentID 10620163
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i91t-a1498f309bb17d5fd079bb32c7703c9ea65ab38fb0052218a62dcfddaf18cd253
IEDL.DBID RIE
IngestDate Wed Aug 27 02:31:52 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i91t-a1498f309bb17d5fd079bb32c7703c9ea65ab38fb0052218a62dcfddaf18cd253
PageCount 8
ParticipantIDs ieee_primary_10620163
PublicationCentury 2000
PublicationDate 2024-May-8
PublicationDateYYYYMMDD 2024-05-08
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-May-8
  day: 08
PublicationDecade 2020
PublicationTitle Intelligent Systems and Computer Vision (Online)
PublicationTitleAbbrev ISCV
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003204120
Score 1.876677
Snippet The study addresses the fundamental challenges encountered in 3D face reconstruction, including the inadequacy of dedicated research initiatives, the...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Computational modeling
Computer architecture
Face recognition
Graph Convolutional Networks (GCNs)
Graph Neural Networks (GNNs)
Hyperparameter optimization
Loss measurement
Optimization Hyperparameter 3D-face Reconstruction
Solid modeling
Three-dimensional displays
Variation Graph Autoencoder (VGAE)
Title Optimization of Graph Convolutional Networks with Variational Graph Autoencoder Architecture for 3D Face Reconstruction Task
URI https://ieeexplore.ieee.org/document/10620163
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcAEiCLe8sCa4sSOHY9VoYCESiWqqlvlp1QBTdXXxI_n7KYtDAxsVhQryTmnu_t832eEbqk2ghipEu8JTZgVNNEp14kUqYP0Wgqnorr-i-h2i-FQ9iqyeuTCOOdi85lrhmHcy7elWQaoDDycQ7zitIZqQvA1WWsLqNAsSEeRqocrJfLu-a09gGw9DXyrjDU3s3-doxLDSOfwny9whBo7Qh7ubUPNMdpzkxP09Qru_lnxKHHp8WMQn8YwZVX9T-oDd9dt3nMcAFc8gMq4Qv-qu1vLRRm0LK2b4daPTQUMySym97ij4NGhRt0pzeK-mr83UL_z0G8_JdVhCslYpotEQSVUeEqk1qmwubdEwJBmRoDLG-kUz5WmhY84MYR9xTNrvLXKp4WxWU5PUX1STtwZwtZqJrngVljFmCOaMa0Lq8EEUBzp_Bw1guVG07VcxmhjtIs_rl-ig7A-sYuwuEJ1-Bp3jfbNajGez27iIn8DyLWrhA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIMEEiCLeeGBNcWInjseqUFpRQiWqqlvlV6QKaFBfEz-es5u2MDCwWVGsJOec7u7zfZ8RuqVKc6KFDPKc0IAZTgMVJioQPLSQXgtupVfX7_AsSwcD0S3J6p4LY631zWe25oZ-L98Ueu6gMvDwBOJVQrfRTsxYRJZ0rTWkQiMnHkXKLq6QiLv2a6MP-XroGFcRq63m_zpJxQeS5sE_X-EQVTeUPNxdB5sjtGXHx-jrBRz-o2RS4iLHj05-GsOURflHyXecLRu9p9hBrrgPtXGJ_5V31-ezwqlZGjvB9R_bChjSWUzvcVPCo12VutGaxT05fauiXvOh12gF5XEKwUiEs0BCLZTmlAilQm7i3BAOQxppDk6vhZVJLBVNc48UQ-CXSWR0bozMw1SbKKYnqDIuxvYUYWMUEwlPDDeSMUsUY0qlRoEJoDxS8RmqOssNP5eCGcOV0c7_uH6D9lq9586w086eLtC-WyvfU5heogp8mb1Cu3oxG00n137BvwHd7a7L
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=Intelligent+Systems+and+Computer+Vision+%28Online%29&rft.atitle=Optimization+of+Graph+Convolutional+Networks+with+Variational+Graph+Autoencoder+Architecture+for+3D+Face+Reconstruction+Task&rft.au=Batarfi%2C+Mahfoudh+M.&rft.au=Mareboyana%2C+Manohar&rft.date=2024-05-08&rft.pub=IEEE&rft.eissn=2768-0754&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FISCV60512.2024.10620163&rft.externalDocID=10620163