GECM: graph embedded convolution model for hand mesh reconstruction

Hand mesh reconstruction from a single RGB image is one of the popular research topic in human understanding field with applications such as virtual/augmented reality and robot operating system. To reconstruct a hand mesh with good quality, we propose a new mesh vertex feature aggregation network mo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal, image and video processing image and video processing, 2023-04, Vol.17 (3), p.715-723
Hauptverfasser: Li, Xuefeng, Lin, Xiangbo, Sun, Yi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 723
container_issue 3
container_start_page 715
container_title Signal, image and video processing
container_volume 17
creator Li, Xuefeng
Lin, Xiangbo
Sun, Yi
description Hand mesh reconstruction from a single RGB image is one of the popular research topic in human understanding field with applications such as virtual/augmented reality and robot operating system. To reconstruct a hand mesh with good quality, we propose a new mesh vertex feature aggregation network module GEC. The current vertex’ features are generated by aggregating the features of the adjacent vertices according to the topological connections of the mesh vertices. Different from the traditional graph convolution structure, the GEC module circumvents the feature vectorization operation, but constructing the topological nodes with the full convolution operation. It has the advantages of avoiding destroying the spatial structure of feature maps and reducing the interference of features in the pseudo-neighborhood. Taking the GEC module as the core module, a new hand mesh reconstruction model GECM is presented. The FreiHAND dataset and the HO-3D dataset are used to evaluate the performance of the proposed GECM model. The experimental results indicate that the GECM model is superior to or on par with the state-of-the-art methods.
doi_str_mv 10.1007/s11760-022-02279-z
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2786132564</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2786132564</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-20b72103726a820f3c5d26fe2d4382f6101a31a0e8f3f8b30005d3ecf11da2553</originalsourceid><addsrcrecordid>eNp9kE1LAzEQhoMoWGr_gKeA59VMprtJvclSW6HiRc8h3ST9oLupya5gf71ZV_TmwDBzeN75eAm5BnYLjIm7CCAKljHO-xSz7HRGRiALzEAAnP_2DC_JJMY9S4FcyEKOSLmYl8_3dBP0cUttvbbGWEMr33z4Q9fufENrb-yBOh_oVjeG1jZuabCJiG3oqh65IhdOH6Kd_NQxeXucv5bLbPWyeCofVlmFMGszztaCA0PBCy05c1jlhhfOcjNFyV0BDDSCZlY6dHKN6crcoK0cgNE8z3FMboa5x-DfOxtbtfddaNJK1X8DyPNimig-UFXwMQbr1DHsah0-FTDV-6UGv1TySn37pU5JhIMoJrjZ2PA3-h_VF6wtbH8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2786132564</pqid></control><display><type>article</type><title>GECM: graph embedded convolution model for hand mesh reconstruction</title><source>SpringerNature Journals</source><creator>Li, Xuefeng ; Lin, Xiangbo ; Sun, Yi</creator><creatorcontrib>Li, Xuefeng ; Lin, Xiangbo ; Sun, Yi</creatorcontrib><description>Hand mesh reconstruction from a single RGB image is one of the popular research topic in human understanding field with applications such as virtual/augmented reality and robot operating system. To reconstruct a hand mesh with good quality, we propose a new mesh vertex feature aggregation network module GEC. The current vertex’ features are generated by aggregating the features of the adjacent vertices according to the topological connections of the mesh vertices. Different from the traditional graph convolution structure, the GEC module circumvents the feature vectorization operation, but constructing the topological nodes with the full convolution operation. It has the advantages of avoiding destroying the spatial structure of feature maps and reducing the interference of features in the pseudo-neighborhood. Taking the GEC module as the core module, a new hand mesh reconstruction model GECM is presented. The FreiHAND dataset and the HO-3D dataset are used to evaluate the performance of the proposed GECM model. The experimental results indicate that the GECM model is superior to or on par with the state-of-the-art methods.</description><identifier>ISSN: 1863-1703</identifier><identifier>EISSN: 1863-1711</identifier><identifier>DOI: 10.1007/s11760-022-02279-z</identifier><language>eng</language><publisher>London: Springer London</publisher><subject>Apexes ; Augmented reality ; Computer Imaging ; Computer Science ; Convolution ; Datasets ; Feature maps ; Finite element method ; Graph theory ; Image Processing and Computer Vision ; Image reconstruction ; Modules ; Multimedia Information Systems ; Original Paper ; Pattern Recognition and Graphics ; Signal,Image and Speech Processing ; Topology ; Virtual reality ; Vision</subject><ispartof>Signal, image and video processing, 2023-04, Vol.17 (3), p.715-723</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022</rights><rights>The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-20b72103726a820f3c5d26fe2d4382f6101a31a0e8f3f8b30005d3ecf11da2553</citedby><cites>FETCH-LOGICAL-c319t-20b72103726a820f3c5d26fe2d4382f6101a31a0e8f3f8b30005d3ecf11da2553</cites><orcidid>0000-0001-7232-9479</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11760-022-02279-z$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11760-022-02279-z$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Li, Xuefeng</creatorcontrib><creatorcontrib>Lin, Xiangbo</creatorcontrib><creatorcontrib>Sun, Yi</creatorcontrib><title>GECM: graph embedded convolution model for hand mesh reconstruction</title><title>Signal, image and video processing</title><addtitle>SIViP</addtitle><description>Hand mesh reconstruction from a single RGB image is one of the popular research topic in human understanding field with applications such as virtual/augmented reality and robot operating system. To reconstruct a hand mesh with good quality, we propose a new mesh vertex feature aggregation network module GEC. The current vertex’ features are generated by aggregating the features of the adjacent vertices according to the topological connections of the mesh vertices. Different from the traditional graph convolution structure, the GEC module circumvents the feature vectorization operation, but constructing the topological nodes with the full convolution operation. It has the advantages of avoiding destroying the spatial structure of feature maps and reducing the interference of features in the pseudo-neighborhood. Taking the GEC module as the core module, a new hand mesh reconstruction model GECM is presented. The FreiHAND dataset and the HO-3D dataset are used to evaluate the performance of the proposed GECM model. The experimental results indicate that the GECM model is superior to or on par with the state-of-the-art methods.</description><subject>Apexes</subject><subject>Augmented reality</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Convolution</subject><subject>Datasets</subject><subject>Feature maps</subject><subject>Finite element method</subject><subject>Graph theory</subject><subject>Image Processing and Computer Vision</subject><subject>Image reconstruction</subject><subject>Modules</subject><subject>Multimedia Information Systems</subject><subject>Original Paper</subject><subject>Pattern Recognition and Graphics</subject><subject>Signal,Image and Speech Processing</subject><subject>Topology</subject><subject>Virtual reality</subject><subject>Vision</subject><issn>1863-1703</issn><issn>1863-1711</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LAzEQhoMoWGr_gKeA59VMprtJvclSW6HiRc8h3ST9oLupya5gf71ZV_TmwDBzeN75eAm5BnYLjIm7CCAKljHO-xSz7HRGRiALzEAAnP_2DC_JJMY9S4FcyEKOSLmYl8_3dBP0cUttvbbGWEMr33z4Q9fufENrb-yBOh_oVjeG1jZuabCJiG3oqh65IhdOH6Kd_NQxeXucv5bLbPWyeCofVlmFMGszztaCA0PBCy05c1jlhhfOcjNFyV0BDDSCZlY6dHKN6crcoK0cgNE8z3FMboa5x-DfOxtbtfddaNJK1X8DyPNimig-UFXwMQbr1DHsah0-FTDV-6UGv1TySn37pU5JhIMoJrjZ2PA3-h_VF6wtbH8</recordid><startdate>20230401</startdate><enddate>20230401</enddate><creator>Li, Xuefeng</creator><creator>Lin, Xiangbo</creator><creator>Sun, Yi</creator><general>Springer London</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-7232-9479</orcidid></search><sort><creationdate>20230401</creationdate><title>GECM: graph embedded convolution model for hand mesh reconstruction</title><author>Li, Xuefeng ; Lin, Xiangbo ; Sun, Yi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-20b72103726a820f3c5d26fe2d4382f6101a31a0e8f3f8b30005d3ecf11da2553</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Apexes</topic><topic>Augmented reality</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Convolution</topic><topic>Datasets</topic><topic>Feature maps</topic><topic>Finite element method</topic><topic>Graph theory</topic><topic>Image Processing and Computer Vision</topic><topic>Image reconstruction</topic><topic>Modules</topic><topic>Multimedia Information Systems</topic><topic>Original Paper</topic><topic>Pattern Recognition and Graphics</topic><topic>Signal,Image and Speech Processing</topic><topic>Topology</topic><topic>Virtual reality</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Xuefeng</creatorcontrib><creatorcontrib>Lin, Xiangbo</creatorcontrib><creatorcontrib>Sun, Yi</creatorcontrib><collection>CrossRef</collection><jtitle>Signal, image and video processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Xuefeng</au><au>Lin, Xiangbo</au><au>Sun, Yi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GECM: graph embedded convolution model for hand mesh reconstruction</atitle><jtitle>Signal, image and video processing</jtitle><stitle>SIViP</stitle><date>2023-04-01</date><risdate>2023</risdate><volume>17</volume><issue>3</issue><spage>715</spage><epage>723</epage><pages>715-723</pages><issn>1863-1703</issn><eissn>1863-1711</eissn><abstract>Hand mesh reconstruction from a single RGB image is one of the popular research topic in human understanding field with applications such as virtual/augmented reality and robot operating system. To reconstruct a hand mesh with good quality, we propose a new mesh vertex feature aggregation network module GEC. The current vertex’ features are generated by aggregating the features of the adjacent vertices according to the topological connections of the mesh vertices. Different from the traditional graph convolution structure, the GEC module circumvents the feature vectorization operation, but constructing the topological nodes with the full convolution operation. It has the advantages of avoiding destroying the spatial structure of feature maps and reducing the interference of features in the pseudo-neighborhood. Taking the GEC module as the core module, a new hand mesh reconstruction model GECM is presented. The FreiHAND dataset and the HO-3D dataset are used to evaluate the performance of the proposed GECM model. The experimental results indicate that the GECM model is superior to or on par with the state-of-the-art methods.</abstract><cop>London</cop><pub>Springer London</pub><doi>10.1007/s11760-022-02279-z</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0001-7232-9479</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1863-1703
ispartof Signal, image and video processing, 2023-04, Vol.17 (3), p.715-723
issn 1863-1703
1863-1711
language eng
recordid cdi_proquest_journals_2786132564
source SpringerNature Journals
subjects Apexes
Augmented reality
Computer Imaging
Computer Science
Convolution
Datasets
Feature maps
Finite element method
Graph theory
Image Processing and Computer Vision
Image reconstruction
Modules
Multimedia Information Systems
Original Paper
Pattern Recognition and Graphics
Signal,Image and Speech Processing
Topology
Virtual reality
Vision
title GECM: graph embedded convolution model for hand mesh reconstruction
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T16%3A32%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GECM:%20graph%20embedded%20convolution%20model%20for%20hand%20mesh%20reconstruction&rft.jtitle=Signal,%20image%20and%20video%20processing&rft.au=Li,%20Xuefeng&rft.date=2023-04-01&rft.volume=17&rft.issue=3&rft.spage=715&rft.epage=723&rft.pages=715-723&rft.issn=1863-1703&rft.eissn=1863-1711&rft_id=info:doi/10.1007/s11760-022-02279-z&rft_dat=%3Cproquest_cross%3E2786132564%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2786132564&rft_id=info:pmid/&rfr_iscdi=true