Portrait Relief Modeling from a Single Image
We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate fo...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on visualization and computer graphics 2020-08, Vol.26 (8), p.2659-2670 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2670 |
|---|---|
| container_issue | 8 |
| container_start_page | 2659 |
| container_title | IEEE transactions on visualization and computer graphics |
| container_volume | 26 |
| creator | Zhang, Yu-Wei Zhang, Caiming Wang, Wenping Chen, Yanzhao Ji, Zhongping Liu, Hui |
| description | We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method. |
| doi_str_mv | 10.1109/TVCG.2019.2892439 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_30640615</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8611145</ieee_id><sourcerecordid>2179350705</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-aaf2588bfd273453468b40e0ec8cb0ac762d3c15c351c0246660d7a783ea015f3</originalsourceid><addsrcrecordid>eNpdkE1Lw0AQhhdRbK3-ABEk4MWDqTP7mT1K0VqoKFq9LtvNpqQkTd00B_-9W1p78DQvzDPDzEPIJcIQEfT97Gs0HlJAPaSZppzpI9JHzTEFAfI4ZlAqpZLKHjlr2yUAcp7pU9JjIDlIFH1y99aETbDlJnn3VemL5KXJY1gtkiI0dWKTj5grn0xqu_Dn5KSwVesv9nVAPp8eZ6PndPo6nowepqljXG9Sawsqsmxe5FQxLhiX2ZyDB-8yNwfrlKQ5cygcE-iAcikl5MqqjHkLKAo2ILe7vevQfHe-3Zi6bJ2vKrvyTdcaikozAQpERG_-ocumC6t4naE8utCcKYwU7igXmrYNvjDrUNY2_BgEs1VptirNVqXZq4wz1_vN3bz2-WHiz10ErnZA6b0_tDOJiPHpX7cRdGI</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2419494371</pqid></control><display><type>article</type><title>Portrait Relief Modeling from a Single Image</title><source>IEEE Electronic Library (IEL)</source><creator>Zhang, Yu-Wei ; Zhang, Caiming ; Wang, Wenping ; Chen, Yanzhao ; Ji, Zhongping ; Liu, Hui</creator><creatorcontrib>Zhang, Yu-Wei ; Zhang, Caiming ; Wang, Wenping ; Chen, Yanzhao ; Ji, Zhongping ; Liu, Hui</creatorcontrib><description>We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method.</description><identifier>ISSN: 1077-2626</identifier><identifier>EISSN: 1941-0506</identifier><identifier>DOI: 10.1109/TVCG.2019.2892439</identifier><identifier>PMID: 30640615</identifier><identifier>CODEN: ITVGEA</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>3D face reconstruction ; Bas-relief modeling ; Computational modeling ; Deformation ; detail recovery ; Face ; Finite element method ; height compression ; high relief modeling ; Image reconstruction ; Modelling ; Shading ; Shape ; Solid modeling ; Strain ; Three dimensional models ; Three-dimensional displays</subject><ispartof>IEEE transactions on visualization and computer graphics, 2020-08, Vol.26 (8), p.2659-2670</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-aaf2588bfd273453468b40e0ec8cb0ac762d3c15c351c0246660d7a783ea015f3</citedby><cites>FETCH-LOGICAL-c349t-aaf2588bfd273453468b40e0ec8cb0ac762d3c15c351c0246660d7a783ea015f3</cites><orcidid>0000-0003-0217-1543 ; 0000-0002-5657-413X ; 0000-0001-6566-5714 ; 0000-0001-7539-6642</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8611145$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8611145$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30640615$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Yu-Wei</creatorcontrib><creatorcontrib>Zhang, Caiming</creatorcontrib><creatorcontrib>Wang, Wenping</creatorcontrib><creatorcontrib>Chen, Yanzhao</creatorcontrib><creatorcontrib>Ji, Zhongping</creatorcontrib><creatorcontrib>Liu, Hui</creatorcontrib><title>Portrait Relief Modeling from a Single Image</title><title>IEEE transactions on visualization and computer graphics</title><addtitle>TVCG</addtitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><description>We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method.</description><subject>3D face reconstruction</subject><subject>Bas-relief modeling</subject><subject>Computational modeling</subject><subject>Deformation</subject><subject>detail recovery</subject><subject>Face</subject><subject>Finite element method</subject><subject>height compression</subject><subject>high relief modeling</subject><subject>Image reconstruction</subject><subject>Modelling</subject><subject>Shading</subject><subject>Shape</subject><subject>Solid modeling</subject><subject>Strain</subject><subject>Three dimensional models</subject><subject>Three-dimensional displays</subject><issn>1077-2626</issn><issn>1941-0506</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkE1Lw0AQhhdRbK3-ABEk4MWDqTP7mT1K0VqoKFq9LtvNpqQkTd00B_-9W1p78DQvzDPDzEPIJcIQEfT97Gs0HlJAPaSZppzpI9JHzTEFAfI4ZlAqpZLKHjlr2yUAcp7pU9JjIDlIFH1y99aETbDlJnn3VemL5KXJY1gtkiI0dWKTj5grn0xqu_Dn5KSwVesv9nVAPp8eZ6PndPo6nowepqljXG9Sawsqsmxe5FQxLhiX2ZyDB-8yNwfrlKQ5cygcE-iAcikl5MqqjHkLKAo2ILe7vevQfHe-3Zi6bJ2vKrvyTdcaikozAQpERG_-ocumC6t4naE8utCcKYwU7igXmrYNvjDrUNY2_BgEs1VptirNVqXZq4wz1_vN3bz2-WHiz10ErnZA6b0_tDOJiPHpX7cRdGI</recordid><startdate>20200801</startdate><enddate>20200801</enddate><creator>Zhang, Yu-Wei</creator><creator>Zhang, Caiming</creator><creator>Wang, Wenping</creator><creator>Chen, Yanzhao</creator><creator>Ji, Zhongping</creator><creator>Liu, Hui</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/0000-0003-0217-1543</orcidid><orcidid>https://orcid.org/0000-0002-5657-413X</orcidid><orcidid>https://orcid.org/0000-0001-6566-5714</orcidid><orcidid>https://orcid.org/0000-0001-7539-6642</orcidid></search><sort><creationdate>20200801</creationdate><title>Portrait Relief Modeling from a Single Image</title><author>Zhang, Yu-Wei ; Zhang, Caiming ; Wang, Wenping ; Chen, Yanzhao ; Ji, Zhongping ; Liu, Hui</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-aaf2588bfd273453468b40e0ec8cb0ac762d3c15c351c0246660d7a783ea015f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>3D face reconstruction</topic><topic>Bas-relief modeling</topic><topic>Computational modeling</topic><topic>Deformation</topic><topic>detail recovery</topic><topic>Face</topic><topic>Finite element method</topic><topic>height compression</topic><topic>high relief modeling</topic><topic>Image reconstruction</topic><topic>Modelling</topic><topic>Shading</topic><topic>Shape</topic><topic>Solid modeling</topic><topic>Strain</topic><topic>Three dimensional models</topic><topic>Three-dimensional displays</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Yu-Wei</creatorcontrib><creatorcontrib>Zhang, Caiming</creatorcontrib><creatorcontrib>Wang, Wenping</creatorcontrib><creatorcontrib>Chen, Yanzhao</creatorcontrib><creatorcontrib>Ji, Zhongping</creatorcontrib><creatorcontrib>Liu, Hui</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>Zhang, Yu-Wei</au><au>Zhang, Caiming</au><au>Wang, Wenping</au><au>Chen, Yanzhao</au><au>Ji, Zhongping</au><au>Liu, Hui</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Portrait Relief Modeling from a Single Image</atitle><jtitle>IEEE transactions on visualization and computer graphics</jtitle><stitle>TVCG</stitle><addtitle>IEEE Trans Vis Comput Graph</addtitle><date>2020-08-01</date><risdate>2020</risdate><volume>26</volume><issue>8</issue><spage>2659</spage><epage>2670</epage><pages>2659-2670</pages><issn>1077-2626</issn><eissn>1941-0506</eissn><coden>ITVGEA</coden><abstract>We present a novel solution to enable portrait relief modeling from a single image. The main challenges are geometry reconstruction, facial details recovery and depth structure preservation. Previous image-based methods are developed for portrait bas-relief modeling in 2.5D form, but not adequate for 3D-like high relief modeling with undercut features. In this paper, we propose a template-based framework to generate portrait reliefs of various forms. Our method benefits from Shape-from-Shading (SFS). Specifically, we use bi-Laplacian mesh deformation to guide the relief modeling. Given a portrait image, we first use a template face to fit the portrait. We then apply bi-Laplacian mesh deformation to align the facial features. Afterwards, SFS-based reconstruction with a few user interactions is used to optimize the face depth, and create a relief with similar appearance to the input. Both depth structures and geometric details can be well constructed in the final relief. Experiments and comparisons to other methods demonstrate the effectiveness of the proposed method.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>30640615</pmid><doi>10.1109/TVCG.2019.2892439</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0003-0217-1543</orcidid><orcidid>https://orcid.org/0000-0002-5657-413X</orcidid><orcidid>https://orcid.org/0000-0001-6566-5714</orcidid><orcidid>https://orcid.org/0000-0001-7539-6642</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1077-2626 |
| ispartof | IEEE transactions on visualization and computer graphics, 2020-08, Vol.26 (8), p.2659-2670 |
| issn | 1077-2626 1941-0506 |
| language | eng |
| recordid | cdi_pubmed_primary_30640615 |
| source | IEEE Electronic Library (IEL) |
| subjects | 3D face reconstruction Bas-relief modeling Computational modeling Deformation detail recovery Face Finite element method height compression high relief modeling Image reconstruction Modelling Shading Shape Solid modeling Strain Three dimensional models Three-dimensional displays |
| title | Portrait Relief Modeling from a Single Image |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T18%3A05%3A54IST&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=Portrait%20Relief%20Modeling%20from%20a%20Single%20Image&rft.jtitle=IEEE%20transactions%20on%20visualization%20and%20computer%20graphics&rft.au=Zhang,%20Yu-Wei&rft.date=2020-08-01&rft.volume=26&rft.issue=8&rft.spage=2659&rft.epage=2670&rft.pages=2659-2670&rft.issn=1077-2626&rft.eissn=1941-0506&rft.coden=ITVGEA&rft_id=info:doi/10.1109/TVCG.2019.2892439&rft_dat=%3Cproquest_RIE%3E2179350705%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=2419494371&rft_id=info:pmid/30640615&rft_ieee_id=8611145&rfr_iscdi=true |