An improved morphable model for 3D face synthesis
We present several improvements on the conventional morphable model. Despite having realistic results and modeling automatically in 3D face synthesis, the model construction depends on the unstable optical flow algorithm; the model is not fitting for complex illumination and the model matching proce...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4367 vol.7 |
|---|---|
| container_issue | |
| container_start_page | 4362 |
| container_title | |
| container_volume | 7 |
| creator | Yong-Li Hu Bao-Cai Yin Shi-Quan Cheng Chun-Liang Gu |
| description | We present several improvements on the conventional morphable model. Despite having realistic results and modeling automatically in 3D face synthesis, the model construction depends on the unstable optical flow algorithm; the model is not fitting for complex illumination and the model matching procedure is time consuming. To improve the morphable model for 3D face synthesis, several measures are taken in this work. Firstly, the mesh resampling method is used to overcome the key problem of model construction, the pixel-to-pixel alignments of prototypic faces. Secondly, based on the mesh resampling data we construct a multi-resolution model to accelerate the model matching procedure and improve the stability of matching convergence. Thirdly, a multi-lights model is proposed to evaluate or simulate the illumination of the input facial image. The experimental results show that these improvements of the morphable model have good performance in 3D face synthesis. |
| doi_str_mv | 10.1109/ICMLC.2004.1384604 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1384604</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1384604</ieee_id><sourcerecordid>1384604</sourcerecordid><originalsourceid>FETCH-LOGICAL-i173t-6f0db1c1d25c35998dd689560b76657f6ad745b9eebaf9e9e407e5fe6cfab2d83</originalsourceid><addsrcrecordid>eNotj8tqwzAURAWl0DbND7Qb_YDdK-u9DO4r4NJNsg6SdUVU7NhIoZC_r6GZzczZzDCEPDGoGQP7sm2_urZuAETNuBEKxA15AG1gAeDNHVmX8gOLuJWqsfeEbU40jXOefjHQccrz0fkBlxRwoHHKlL_S6Hqk5XI6H7Gk8khuoxsKrq--Ivv3t137WXXfH9t201WJaX6uVITgWc9CI3surTUhKLOMgtdKSR2VC1pIbxG9ixYtCtAoI6o-Ot8Ew1fk-b83IeJhzml0-XK4vuJ_DghCkQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>An improved morphable model for 3D face synthesis</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Yong-Li Hu ; Bao-Cai Yin ; Shi-Quan Cheng ; Chun-Liang Gu</creator><creatorcontrib>Yong-Li Hu ; Bao-Cai Yin ; Shi-Quan Cheng ; Chun-Liang Gu</creatorcontrib><description>We present several improvements on the conventional morphable model. Despite having realistic results and modeling automatically in 3D face synthesis, the model construction depends on the unstable optical flow algorithm; the model is not fitting for complex illumination and the model matching procedure is time consuming. To improve the morphable model for 3D face synthesis, several measures are taken in this work. Firstly, the mesh resampling method is used to overcome the key problem of model construction, the pixel-to-pixel alignments of prototypic faces. Secondly, based on the mesh resampling data we construct a multi-resolution model to accelerate the model matching procedure and improve the stability of matching convergence. Thirdly, a multi-lights model is proposed to evaluate or simulate the illumination of the input facial image. The experimental results show that these improvements of the morphable model have good performance in 3D face synthesis.</description><identifier>ISBN: 0780384032</identifier><identifier>ISBN: 9780780384033</identifier><identifier>DOI: 10.1109/ICMLC.2004.1384604</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acceleration ; Computational modeling ; Deformable models ; Electronic mail ; Face ; Facial animation ; Humans ; Laboratories ; Lighting ; Prototypes</subject><ispartof>Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826), 2004, Vol.7, p.4362-4367 vol.7</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1384604$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,4048,4049,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1384604$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yong-Li Hu</creatorcontrib><creatorcontrib>Bao-Cai Yin</creatorcontrib><creatorcontrib>Shi-Quan Cheng</creatorcontrib><creatorcontrib>Chun-Liang Gu</creatorcontrib><title>An improved morphable model for 3D face synthesis</title><title>Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826)</title><addtitle>ICMLC</addtitle><description>We present several improvements on the conventional morphable model. Despite having realistic results and modeling automatically in 3D face synthesis, the model construction depends on the unstable optical flow algorithm; the model is not fitting for complex illumination and the model matching procedure is time consuming. To improve the morphable model for 3D face synthesis, several measures are taken in this work. Firstly, the mesh resampling method is used to overcome the key problem of model construction, the pixel-to-pixel alignments of prototypic faces. Secondly, based on the mesh resampling data we construct a multi-resolution model to accelerate the model matching procedure and improve the stability of matching convergence. Thirdly, a multi-lights model is proposed to evaluate or simulate the illumination of the input facial image. The experimental results show that these improvements of the morphable model have good performance in 3D face synthesis.</description><subject>Acceleration</subject><subject>Computational modeling</subject><subject>Deformable models</subject><subject>Electronic mail</subject><subject>Face</subject><subject>Facial animation</subject><subject>Humans</subject><subject>Laboratories</subject><subject>Lighting</subject><subject>Prototypes</subject><isbn>0780384032</isbn><isbn>9780780384033</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj8tqwzAURAWl0DbND7Qb_YDdK-u9DO4r4NJNsg6SdUVU7NhIoZC_r6GZzczZzDCEPDGoGQP7sm2_urZuAETNuBEKxA15AG1gAeDNHVmX8gOLuJWqsfeEbU40jXOefjHQccrz0fkBlxRwoHHKlL_S6Hqk5XI6H7Gk8khuoxsKrq--Ivv3t137WXXfH9t201WJaX6uVITgWc9CI3surTUhKLOMgtdKSR2VC1pIbxG9ixYtCtAoI6o-Ot8Ew1fk-b83IeJhzml0-XK4vuJ_DghCkQ</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Yong-Li Hu</creator><creator>Bao-Cai Yin</creator><creator>Shi-Quan Cheng</creator><creator>Chun-Liang Gu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2004</creationdate><title>An improved morphable model for 3D face synthesis</title><author>Yong-Li Hu ; Bao-Cai Yin ; Shi-Quan Cheng ; Chun-Liang Gu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i173t-6f0db1c1d25c35998dd689560b76657f6ad745b9eebaf9e9e407e5fe6cfab2d83</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Acceleration</topic><topic>Computational modeling</topic><topic>Deformable models</topic><topic>Electronic mail</topic><topic>Face</topic><topic>Facial animation</topic><topic>Humans</topic><topic>Laboratories</topic><topic>Lighting</topic><topic>Prototypes</topic><toplevel>online_resources</toplevel><creatorcontrib>Yong-Li Hu</creatorcontrib><creatorcontrib>Bao-Cai Yin</creatorcontrib><creatorcontrib>Shi-Quan Cheng</creatorcontrib><creatorcontrib>Chun-Liang Gu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yong-Li Hu</au><au>Bao-Cai Yin</au><au>Shi-Quan Cheng</au><au>Chun-Liang Gu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>An improved morphable model for 3D face synthesis</atitle><btitle>Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826)</btitle><stitle>ICMLC</stitle><date>2004</date><risdate>2004</risdate><volume>7</volume><spage>4362</spage><epage>4367 vol.7</epage><pages>4362-4367 vol.7</pages><isbn>0780384032</isbn><isbn>9780780384033</isbn><abstract>We present several improvements on the conventional morphable model. Despite having realistic results and modeling automatically in 3D face synthesis, the model construction depends on the unstable optical flow algorithm; the model is not fitting for complex illumination and the model matching procedure is time consuming. To improve the morphable model for 3D face synthesis, several measures are taken in this work. Firstly, the mesh resampling method is used to overcome the key problem of model construction, the pixel-to-pixel alignments of prototypic faces. Secondly, based on the mesh resampling data we construct a multi-resolution model to accelerate the model matching procedure and improve the stability of matching convergence. Thirdly, a multi-lights model is proposed to evaluate or simulate the illumination of the input facial image. The experimental results show that these improvements of the morphable model have good performance in 3D face synthesis.</abstract><pub>IEEE</pub><doi>10.1109/ICMLC.2004.1384604</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780384032 |
| ispartof | Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826), 2004, Vol.7, p.4362-4367 vol.7 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_1384604 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Acceleration Computational modeling Deformable models Electronic mail Face Facial animation Humans Laboratories Lighting Prototypes |
| title | An improved morphable model for 3D face synthesis |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T02%3A01%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=An%20improved%20morphable%20model%20for%203D%20face%20synthesis&rft.btitle=Proceedings%20of%202004%20International%20Conference%20on%20Machine%20Learning%20and%20Cybernetics%20(IEEE%20Cat.%20No.04EX826)&rft.au=Yong-Li%20Hu&rft.date=2004&rft.volume=7&rft.spage=4362&rft.epage=4367%20vol.7&rft.pages=4362-4367%20vol.7&rft.isbn=0780384032&rft.isbn_list=9780780384033&rft_id=info:doi/10.1109/ICMLC.2004.1384604&rft_dat=%3Cieee_6IE%3E1384604%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1384604&rfr_iscdi=true |