Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models
Identifieur interne : 001B47 ( Istex/Corpus ); précédent : 001B46; suivant : 001B48Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models
Auteurs : F. Lavagetto ; R. Pockaj ; M. CostaSource :
- Image and Vision Computing [ 0262-8856 ] ; 1999.
English descriptors
- KwdEn :
Abstract
The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters. A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.
Url:
DOI: 10.1016/S0262-8856(99)00054-2
Links to Exploration step
ISTEX:2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26FLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title><author><name sortKey="Lavagetto, F" sort="Lavagetto, F" uniqKey="Lavagetto F" first="F." last="Lavagetto">F. Lavagetto</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author><author><name sortKey="Pockaj, R" sort="Pockaj, R" uniqKey="Pockaj R" first="R." last="Pockaj">R. Pockaj</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author><author><name sortKey="Costa, M" sort="Costa, M" uniqKey="Costa M" first="M." last="Costa">M. Costa</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F</idno><date when="2000" year="2000">2000</date><idno type="doi">10.1016/S0262-8856(99)00054-2</idno><idno type="url">https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001B47</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title><author><name sortKey="Lavagetto, F" sort="Lavagetto, F" uniqKey="Lavagetto F" first="F." last="Lavagetto">F. Lavagetto</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author><author><name sortKey="Pockaj, R" sort="Pockaj, R" uniqKey="Pockaj R" first="R." last="Pockaj">R. Pockaj</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author><author><name sortKey="Costa, M" sort="Costa, M" uniqKey="Costa M" first="M." last="Costa">M. Costa</name><affiliation><mods:affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: fabio@dist.unige.it</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Image and Vision Computing</title><title level="j" type="abbrev">IMAVIS</title><idno type="ISSN">0262-8856</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1999">1999</date><biblScope unit="volume">18</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="345">345</biblScope><biblScope unit="page" to="353">353</biblScope></imprint><idno type="ISSN">0262-8856</idno></series><idno type="istex">2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F</idno><idno type="DOI">10.1016/S0262-8856(99)00054-2</idno><idno type="PII">S0262-8856(99)00054-2</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0262-8856</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Facial animation</term><term>Motion picture expert group-4</term><term>Smooth surface interpolation</term><term>Texture adaptation</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters. A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>F. Lavagetto</name><affiliations><json:string>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</json:string><json:string>E-mail: fabio@dist.unige.it</json:string></affiliations></json:item><json:item><name>R. Pockaj</name><affiliations><json:string>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</json:string><json:string>E-mail: fabio@dist.unige.it</json:string></affiliations></json:item><json:item><name>M. Costa</name><affiliations><json:string>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</json:string><json:string>E-mail: fabio@dist.unige.it</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Smooth surface interpolation</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Texture adaptation</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Motion picture expert group-4</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Facial animation</value></json:item></subject><language><json:string>eng</json:string></language><abstract>The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters. A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.</abstract><qualityIndicators><score>7.062</score><pdfVersion>1.2</pdfVersion><pdfPageSize>595 x 794 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>4</keywordCount><abstractCharCount>1657</abstractCharCount><pdfWordCount>4110</pdfWordCount><pdfCharCount>23627</pdfCharCount><pdfPageCount>9</pdfPageCount><abstractWordCount>246</abstractWordCount></qualityIndicators><title>Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title><pii><json:string>S0262-8856(99)00054-2</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>18</volume><pii><json:string>S0262-8856(00)X0059-5</json:string></pii><pages><last>353</last><first>345</first></pages><issn><json:string>0262-8856</json:string></issn><issue>4</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Image and Vision Computing</title><publicationDate>2000</publicationDate></host><categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string><json:string>COMPUTER SCIENCE, SOFTWARE ENGINEERING</json:string><json:string>COMPUTER SCIENCE, THEORY & METHODS</json:string><json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string><json:string>OPTICS</json:string></wos></categories><publicationDate>1999</publicationDate><copyrightDate>2000</copyrightDate><doi><json:string>10.1016/S0262-8856(99)00054-2</json:string></doi><id>2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/fulltext/pdf</uri></json:item><json:item><original>true</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/fulltext/txt</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>2000</date></publicationStmt><notesStmt><note type="content">Fig. 1: Example of MPEG-4 scene graph with composition of synthetic objects (the virtual actor, text and graphics overlay) and natural video as background.</note><note type="content">Fig. 2: Rendering of the scene described by the MPEG-4 scene graph of Fig. 1.</note><note type="content">Fig. 3: Example of Neutral Face, obtained on the “Oscar” model.</note><note type="content">Fig. 4: Description of the feature points standardized MPEG-4.</note><note type="content">Fig. 5: Wire-frame of “Mike” (left) and “Oscar” (right).</note><note type="content">Fig. 6: Example of multi-step calibration of the model “Oscar” on “Claude” feature points. After the first iteration (top), calibration is still weak in correspondence to the nose, eyes, forehead and ears. Smooth but precise reproduction of details is gained after the second (center) and third (bottom) iteration.</note><note type="content">Fig. 7: (Left) Front and side view of “Cyrano” [13]; calibration of the model “Mike” (center) and of the model “Oscar” (right) on the feature points extracted from “Cyrano”. The version of the model “Oscar” employed in the calibration was still preliminary and still incomplete.</note><note type="content">Fig. 8: Examples of texture extracted from a 3D scanner (left) and from a 2D picture (right).</note><note type="content">Fig. 9: Example of incorrect mapping of the natural texture onto the model eye-ball (left) and of the result achieved through the separate texture mapping for the eye region (right).</note><note type="content">Fig. 10: (Top) Examples of incorrect texture mapping on the hair region of the “Mike” model. Artifacts are evident in correspondence to the boundary between the forehead and the hair where some texture of the forehead skin is mapped on the model hair polygons. Artifacts are present also in correspondence to the back part of the head due to missing cyber-scan information. (Bottom) Result achieved through the developed technique for separate texture mapping of the hair region.</note><note type="content">Fig. 11: (Top) Frontal and side views of the texture calibration target “Claude” [13]; (center) model “Oscar” reshaped with the feature points of “Claude”; (bottom) model “Oscar” reshaped with feature points and with the texture of “Claude”.</note><note type="content">Fig. 12: (Top) Frontal and side views of the texture calibration target “Chen” [13]; (center) model “Oscar” reshaped with the feature points of “Chen”; (bottom) model “Oscar” reshaped with feature points and with the texture of “Chen”.</note><note type="content">Table 1: Feature points description table</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title><author><persName><forename type="first">F.</forename><surname>Lavagetto</surname></persName><email>fabio@dist.unige.it</email><note type="correspondence"><p>Corresponding author</p></note><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation></author><author><persName><forename type="first">R.</forename><surname>Pockaj</surname></persName><email>fabio@dist.unige.it</email><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation></author><author><persName><forename type="first">M.</forename><surname>Costa</surname></persName><email>fabio@dist.unige.it</email><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation></author></analytic><monogr><title level="j">Image and Vision Computing</title><title level="j" type="abbrev">IMAVIS</title><idno type="pISSN">0262-8856</idno><idno type="PII">S0262-8856(00)X0059-5</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1999"></date><biblScope unit="volume">18</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="345">345</biblScope><biblScope unit="page" to="353">353</biblScope></imprint></monogr><idno type="istex">2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F</idno><idno type="DOI">10.1016/S0262-8856(99)00054-2</idno><idno type="PII">S0262-8856(99)00054-2</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2000</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters. A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.</p></abstract><textClass xml:lang="en"><keywords scheme="keyword"><list><head>Keywords</head><item><term>Smooth surface interpolation</term></item><item><term>Texture adaptation</term></item><item><term>Motion picture expert group-4</term></item><item><term>Facial animation</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="1999-07-13">Registration</change><change when="1999-06-30">Modified</change><change when="1999">Published</change></revisionDesc></teiHeader></istex:fulltextTEI></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: ce:floats; body; tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"><istex:entity SYSTEM="gr1" NDATA="IMAGE" name="gr1"></istex:entity><istex:entity SYSTEM="gr2" NDATA="IMAGE" name="gr2"></istex:entity><istex:entity SYSTEM="gr3" NDATA="IMAGE" name="gr3"></istex:entity><istex:entity SYSTEM="gr4" NDATA="IMAGE" name="gr4"></istex:entity><istex:entity SYSTEM="gr5" NDATA="IMAGE" name="gr5"></istex:entity><istex:entity SYSTEM="gr6" NDATA="IMAGE" name="gr6"></istex:entity><istex:entity SYSTEM="gr7" NDATA="IMAGE" name="gr7"></istex:entity><istex:entity SYSTEM="gr8" NDATA="IMAGE" name="gr8"></istex:entity><istex:entity SYSTEM="gr9" NDATA="IMAGE" name="gr9"></istex:entity><istex:entity SYSTEM="gr10" NDATA="IMAGE" name="gr10"></istex:entity><istex:entity SYSTEM="gr11" NDATA="IMAGE" name="gr11"></istex:entity><istex:entity SYSTEM="gr12" NDATA="IMAGE" name="gr12"></istex:entity></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="fla" xml:lang="en"><item-info><jid>IMAVIS</jid><aid>1674</aid><ce:pii>S0262-8856(99)00054-2</ce:pii><ce:doi>10.1016/S0262-8856(99)00054-2</ce:doi><ce:copyright type="full-transfer" year="2000">Elsevier Science B.V.</ce:copyright></item-info><head><ce:title>Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</ce:title><ce:author-group><ce:author><ce:given-name>F.</ce:given-name><ce:surname>Lavagetto</ce:surname><ce:cross-ref refid="CORR1">*</ce:cross-ref><ce:e-address>fabio@dist.unige.it</ce:e-address></ce:author><ce:author><ce:given-name>R.</ce:given-name><ce:surname>Pockaj</ce:surname><ce:e-address>pok@dist.unige.it</ce:e-address></ce:author><ce:author><ce:given-name>M.</ce:given-name><ce:surname>Costa</ce:surname><ce:e-address>cattivik@dist.unige.it</ce:e-address></ce:author><ce:affiliation><ce:textfn>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</ce:textfn></ce:affiliation><ce:correspondence id="CORR1"><ce:label>*</ce:label><ce:text>Corresponding author</ce:text></ce:correspondence></ce:author-group><ce:date-received day="29" month="9" year="1998"></ce:date-received><ce:date-revised day="30" month="6" year="1999"></ce:date-revised><ce:date-accepted day="13" month="7" year="1999"></ce:date-accepted><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters.</ce:simple-para><ce:simple-para>A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords class="keyword" xml:lang="en"><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>Smooth surface interpolation</ce:text></ce:keyword><ce:keyword><ce:text>Texture adaptation</ce:text></ce:keyword><ce:keyword><ce:text>Motion picture expert group-4</ce:text></ce:keyword><ce:keyword><ce:text>Facial animation</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title></titleInfo><titleInfo type="alternative" lang="en" contentType="CDATA"><title>Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models</title></titleInfo><name type="personal"><namePart type="given">F.</namePart><namePart type="family">Lavagetto</namePart><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation><affiliation>E-mail: fabio@dist.unige.it</affiliation><description>Corresponding author</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">R.</namePart><namePart type="family">Pockaj</namePart><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation><affiliation>E-mail: fabio@dist.unige.it</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">M.</namePart><namePart type="family">Costa</namePart><affiliation>DIST, University of Genova, via Opera Pia 13, 16145 Genova, Italy</affiliation><affiliation>E-mail: fabio@dist.unige.it</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="Full-length article"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">1999</dateIssued><dateValid encoding="w3cdtf">1999-07-13</dateValid><dateModified encoding="w3cdtf">1999-06-30</dateModified><copyrightDate encoding="w3cdtf">2000</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">The technique proposed in this paper provides operative indications for implementing 3D head models compliant to face parameters recently standardized in Motion Picture Expert Group, MPEG-4, and capable of being calibrated on any specific human face. Since the set of calibration guide points, defined in MPEG-4 as feature points, is very limited with reference to the complexity of the human head geometry, suitable interpolation must be performed to assure smooth and realistic surface rendering. On the other hand, care must be paid in texture adaptation to avoid annoying artifacts in correspondence to deformable face features, which are even more appreciable when the model is animated. The proposed methodology is based on the use of Radical Basis Functions (RBF) for smooth surface interpolation, applied according to a multi-step procedure for progressive detail definition. The set of interpolating functions has been derived empirically exploiting a priori knowledge on the geometry of human heads. The adaptation of the texture information, achieved using the MPEG-4 feature points as anchor points, is also performed according to a multi-step fashion by organizing the head model polygons into homogeneous subsets (i.e. polygons of the hair region define a specific subset). Experimental results, as reported in the following, prove the effectiveness of the proposed method showing how it is possible to adapt the same generic model to different face parameters. A variety of applications is envisaged in multimedia products, virtual and augmented reality, very low bitrate videophone and efficient three-dimensional (3D) facial data archiving.</abstract><note type="content">Fig. 1: Example of MPEG-4 scene graph with composition of synthetic objects (the virtual actor, text and graphics overlay) and natural video as background.</note><note type="content">Fig. 2: Rendering of the scene described by the MPEG-4 scene graph of Fig. 1.</note><note type="content">Fig. 3: Example of Neutral Face, obtained on the “Oscar” model.</note><note type="content">Fig. 4: Description of the feature points standardized MPEG-4.</note><note type="content">Fig. 5: Wire-frame of “Mike” (left) and “Oscar” (right).</note><note type="content">Fig. 6: Example of multi-step calibration of the model “Oscar” on “Claude” feature points. After the first iteration (top), calibration is still weak in correspondence to the nose, eyes, forehead and ears. Smooth but precise reproduction of details is gained after the second (center) and third (bottom) iteration.</note><note type="content">Fig. 7: (Left) Front and side view of “Cyrano” [13]; calibration of the model “Mike” (center) and of the model “Oscar” (right) on the feature points extracted from “Cyrano”. The version of the model “Oscar” employed in the calibration was still preliminary and still incomplete.</note><note type="content">Fig. 8: Examples of texture extracted from a 3D scanner (left) and from a 2D picture (right).</note><note type="content">Fig. 9: Example of incorrect mapping of the natural texture onto the model eye-ball (left) and of the result achieved through the separate texture mapping for the eye region (right).</note><note type="content">Fig. 10: (Top) Examples of incorrect texture mapping on the hair region of the “Mike” model. Artifacts are evident in correspondence to the boundary between the forehead and the hair where some texture of the forehead skin is mapped on the model hair polygons. Artifacts are present also in correspondence to the back part of the head due to missing cyber-scan information. (Bottom) Result achieved through the developed technique for separate texture mapping of the hair region.</note><note type="content">Fig. 11: (Top) Frontal and side views of the texture calibration target “Claude” [13]; (center) model “Oscar” reshaped with the feature points of “Claude”; (bottom) model “Oscar” reshaped with feature points and with the texture of “Claude”.</note><note type="content">Fig. 12: (Top) Frontal and side views of the texture calibration target “Chen” [13]; (center) model “Oscar” reshaped with the feature points of “Chen”; (bottom) model “Oscar” reshaped with feature points and with the texture of “Chen”.</note><note type="content">Table 1: Feature points description table</note><subject lang="en"><genre>Keywords</genre><topic>Smooth surface interpolation</topic><topic>Texture adaptation</topic><topic>Motion picture expert group-4</topic><topic>Facial animation</topic></subject><relatedItem type="host"><titleInfo><title>Image and Vision Computing</title></titleInfo><titleInfo type="abbreviated"><title>IMAVIS</title></titleInfo><genre type="Journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">20000301</dateIssued></originInfo><identifier type="ISSN">0262-8856</identifier><identifier type="PII">S0262-8856(00)X0059-5</identifier><part><date>20000301</date><detail type="volume"><number>18</number><caption>vol.</caption></detail><detail type="issue"><number>4</number><caption>no.</caption></detail><extent unit="issue pages"><start>271</start><end>364</end></extent><extent unit="pages"><start>345</start><end>353</end></extent></part></relatedItem><identifier type="istex">2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F</identifier><identifier type="DOI">10.1016/S0262-8856(99)00054-2</identifier><identifier type="PII">S0262-8856(99)00054-2</identifier><accessCondition type="use and reproduction" contentType="">© 2000Elsevier Science B.V.</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Elsevier Science B.V., ©2000</recordOrigin></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode><classCode scheme="WOS">COMPUTER SCIENCE, SOFTWARE ENGINEERING</classCode><classCode scheme="WOS">COMPUTER SCIENCE, THEORY & METHODS</classCode><classCode scheme="WOS">ENGINEERING, ELECTRICAL & ELECTRONIC</classCode><classCode scheme="WOS">OPTICS</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI></enrichments><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Musique/explor/OperaV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001B47 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 001B47 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Musique
|area= OperaV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:2ED1BAC39546AE3DDE2F93E632CC42ED28A5B26F
|texte= Smooth surface interpolation and texture adaptation for MPEG-4 compliant calibration of 3D head models
}}
| This area was generated with Dilib version V0.6.21. |  |