Plausible 3D Face Wrinkle Generation Using Variational Autoencoders
Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolve...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on visualization and computer graphics 2022-09, Vol.28 (9), p.3113-3125 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3125 |
|---|---|
| container_issue | 9 |
| container_start_page | 3113 |
| container_title | IEEE transactions on visualization and computer graphics |
| container_volume | 28 |
| creator | Deng, Qixin Ma, Luming Jin, Aobo Bi, Huikun Le, Binh Huy Deng, Zhigang |
| description | Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions. |
| doi_str_mv | 10.1109/TVCG.2021.3051251 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_33439847</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9321747</ieee_id><sourcerecordid>2696284618</sourcerecordid><originalsourceid>FETCH-LOGICAL-c392t-bf2f255e59c8cad7aa61824d557e7a8a22ace4b9e5017f70bc8ca4b49011d98b3</originalsourceid><addsrcrecordid>eNpdkEtPwkAQgDdGI4j-AGNimnjxUtzZR7d7JFXQhEQPgMdm205NsbS42x789y6CHDzNTOabRz5CroGOAah-WKyS2ZhRBmNOJTAJJ2QIWkBIJY1OfU6VClnEogG5cG5NKQgR63My4FxwHQs1JMlbbXpXZTUG_DGYmhyDd1s1n76eYYPWdFXbBEtXNR_BytjqtzZ1MOm7Fpu8LdC6S3JWmtrh1SGOyHL6tEiew_nr7CWZzMOca9aFWclKJiVKnce5KZQxEcRMFFIqVCY2jPnrItMoKahS0WyHiUxoClDoOOMjcr_fu7XtV4-uSzeVy7GuTYNt71ImVEy5lKA8evcPXbe99Y97KtIRi4W_7SnYU7ltnbNYpltbbYz9ToGmO8PpznC6M5weDPuZ28PmPttgcZz4U-qBmz1QIeKxrTkD5bs_xI1-DQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2696284618</pqid></control><display><type>article</type><title>Plausible 3D Face Wrinkle Generation Using Variational Autoencoders</title><source>IEEE Electronic Library (IEL)</source><creator>Deng, Qixin ; Ma, Luming ; Jin, Aobo ; Bi, Huikun ; Le, Binh Huy ; Deng, Zhigang</creator><creatorcontrib>Deng, Qixin ; Ma, Luming ; Jin, Aobo ; Bi, Huikun ; Le, Binh Huy ; Deng, Zhigang</creatorcontrib><description>Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.</description><identifier>ISSN: 1077-2626</identifier><identifier>EISSN: 1941-0506</identifier><identifier>DOI: 10.1109/TVCG.2021.3051251</identifier><identifier>PMID: 33439847</identifier><identifier>CODEN: ITVGEA</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Animation ; Computational modeling ; Data models ; deep generative models ; Face modeling ; Faces ; Interpolation ; Pipelines ; Shape ; Solid modeling ; Synthesis ; Three dimensional models ; Three-dimensional displays ; Topology ; variational autoencoders ; Virtual reality ; wrinkle synthesis</subject><ispartof>IEEE transactions on visualization and computer graphics, 2022-09, Vol.28 (9), p.3113-3125</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c392t-bf2f255e59c8cad7aa61824d557e7a8a22ace4b9e5017f70bc8ca4b49011d98b3</citedby><cites>FETCH-LOGICAL-c392t-bf2f255e59c8cad7aa61824d557e7a8a22ace4b9e5017f70bc8ca4b49011d98b3</cites><orcidid>0000-0002-0690-4663 ; 0000-0003-2571-5865</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9321747$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9321747$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33439847$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Deng, Qixin</creatorcontrib><creatorcontrib>Ma, Luming</creatorcontrib><creatorcontrib>Jin, Aobo</creatorcontrib><creatorcontrib>Bi, Huikun</creatorcontrib><creatorcontrib>Le, Binh Huy</creatorcontrib><creatorcontrib>Deng, Zhigang</creatorcontrib><title>Plausible 3D Face Wrinkle Generation Using Variational Autoencoders</title><title>IEEE transactions on visualization and computer graphics</title><addtitle>TVCG</addtitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><description>Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.</description><subject>Animation</subject><subject>Computational modeling</subject><subject>Data models</subject><subject>deep generative models</subject><subject>Face modeling</subject><subject>Faces</subject><subject>Interpolation</subject><subject>Pipelines</subject><subject>Shape</subject><subject>Solid modeling</subject><subject>Synthesis</subject><subject>Three dimensional models</subject><subject>Three-dimensional displays</subject><subject>Topology</subject><subject>variational autoencoders</subject><subject>Virtual reality</subject><subject>wrinkle synthesis</subject><issn>1077-2626</issn><issn>1941-0506</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkEtPwkAQgDdGI4j-AGNimnjxUtzZR7d7JFXQhEQPgMdm205NsbS42x789y6CHDzNTOabRz5CroGOAah-WKyS2ZhRBmNOJTAJJ2QIWkBIJY1OfU6VClnEogG5cG5NKQgR63My4FxwHQs1JMlbbXpXZTUG_DGYmhyDd1s1n76eYYPWdFXbBEtXNR_BytjqtzZ1MOm7Fpu8LdC6S3JWmtrh1SGOyHL6tEiew_nr7CWZzMOca9aFWclKJiVKnce5KZQxEcRMFFIqVCY2jPnrItMoKahS0WyHiUxoClDoOOMjcr_fu7XtV4-uSzeVy7GuTYNt71ImVEy5lKA8evcPXbe99Y97KtIRi4W_7SnYU7ltnbNYpltbbYz9ToGmO8PpznC6M5weDPuZ28PmPttgcZz4U-qBmz1QIeKxrTkD5bs_xI1-DQ</recordid><startdate>20220901</startdate><enddate>20220901</enddate><creator>Deng, Qixin</creator><creator>Ma, Luming</creator><creator>Jin, Aobo</creator><creator>Bi, Huikun</creator><creator>Le, Binh Huy</creator><creator>Deng, Zhigang</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-0690-4663</orcidid><orcidid>https://orcid.org/0000-0003-2571-5865</orcidid></search><sort><creationdate>20220901</creationdate><title>Plausible 3D Face Wrinkle Generation Using Variational Autoencoders</title><author>Deng, Qixin ; Ma, Luming ; Jin, Aobo ; Bi, Huikun ; Le, Binh Huy ; Deng, Zhigang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c392t-bf2f255e59c8cad7aa61824d557e7a8a22ace4b9e5017f70bc8ca4b49011d98b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Animation</topic><topic>Computational modeling</topic><topic>Data models</topic><topic>deep generative models</topic><topic>Face modeling</topic><topic>Faces</topic><topic>Interpolation</topic><topic>Pipelines</topic><topic>Shape</topic><topic>Solid modeling</topic><topic>Synthesis</topic><topic>Three dimensional models</topic><topic>Three-dimensional displays</topic><topic>Topology</topic><topic>variational autoencoders</topic><topic>Virtual reality</topic><topic>wrinkle synthesis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Deng, Qixin</creatorcontrib><creatorcontrib>Ma, Luming</creatorcontrib><creatorcontrib>Jin, Aobo</creatorcontrib><creatorcontrib>Bi, Huikun</creatorcontrib><creatorcontrib>Le, Binh Huy</creatorcontrib><creatorcontrib>Deng, Zhigang</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on visualization and computer graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Deng, Qixin</au><au>Ma, Luming</au><au>Jin, Aobo</au><au>Bi, Huikun</au><au>Le, Binh Huy</au><au>Deng, Zhigang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Plausible 3D Face Wrinkle Generation Using Variational Autoencoders</atitle><jtitle>IEEE transactions on visualization and computer graphics</jtitle><stitle>TVCG</stitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><date>2022-09-01</date><risdate>2022</risdate><volume>28</volume><issue>9</issue><spage>3113</spage><epage>3125</epage><pages>3113-3125</pages><issn>1077-2626</issn><eissn>1941-0506</eissn><coden>ITVGEA</coden><abstract>Realistic 3D facial modeling and animation have been increasingly used in many graphics, animation, and virtual reality applications. However, generating realistic fine-scale wrinkles on 3D faces, in particular, on animated 3D faces, is still a challenging problem that is far away from being resolved. In this article we propose an end-to-end system to automatically augment coarse-scale 3D faces with synthesized fine-scale geometric wrinkles. By formulating the wrinkle generation problem as a supervised generation task, we implicitly model the continuous space of face wrinkles via a compact generative model, such that plausible face wrinkles can be generated through effective sampling and interpolation in the space. We also introduce a complete pipeline to transfer the synthesized wrinkles between faces with different shapes and topologies. Through many experiments, we demonstrate our method can robustly synthesize plausible fine-scale wrinkles on a variety of coarse-scale 3D faces with different shapes and expressions.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>33439847</pmid><doi>10.1109/TVCG.2021.3051251</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0002-0690-4663</orcidid><orcidid>https://orcid.org/0000-0003-2571-5865</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1077-2626 |
| ispartof | IEEE transactions on visualization and computer graphics, 2022-09, Vol.28 (9), p.3113-3125 |
| issn | 1077-2626 1941-0506 |
| language | eng |
| recordid | cdi_pubmed_primary_33439847 |
| source | IEEE Electronic Library (IEL) |
| subjects | Animation Computational modeling Data models deep generative models Face modeling Faces Interpolation Pipelines Shape Solid modeling Synthesis Three dimensional models Three-dimensional displays Topology variational autoencoders Virtual reality wrinkle synthesis |
| title | Plausible 3D Face Wrinkle Generation Using Variational Autoencoders |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T20%3A01%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Plausible%203D%20Face%20Wrinkle%20Generation%20Using%20Variational%20Autoencoders&rft.jtitle=IEEE%20transactions%20on%20visualization%20and%20computer%20graphics&rft.au=Deng,%20Qixin&rft.date=2022-09-01&rft.volume=28&rft.issue=9&rft.spage=3113&rft.epage=3125&rft.pages=3113-3125&rft.issn=1077-2626&rft.eissn=1941-0506&rft.coden=ITVGEA&rft_id=info:doi/10.1109/TVCG.2021.3051251&rft_dat=%3Cproquest_RIE%3E2696284618%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2696284618&rft_id=info:pmid/33439847&rft_ieee_id=9321747&rfr_iscdi=true |