A Superresolution Framework for High-Accuracy Multiview Reconstruction

dc.contributor.authorGoldlücke, Bastian
dc.contributor.authorCremers, Daniel
dc.date.accessioned2017-12-06T10:20:47Z
dc.date.available2017-12-06T10:20:47Z
dc.date.issued2009eng
dc.description.abstractWe present a variational approach to jointly estimate a displacement map and a superresolution texture for a 3D model from multiple calibrated views. The superresolution image formation model leads to an energy functional defined in terms of an integral over the object surface. This functional can be minimized by alternately solving a deblurring PDE and a total variation minimization on the surface, leading to increasingly accurate estimates of photometry and geometry, respectively. The resulting equations can be discretized and solved on texture space with the help of a conformal atlas. The superresolution approach to texture reconstruction allows to obtain fine details in the texture map which surpass individual input image resolution.eng
dc.description.versionpublishedeng
dc.identifier.doi10.1007/978-3-642-03798-6_35eng
dc.identifier.urihttps://kops.uni-konstanz.de/handle/123456789/40857
dc.language.isoengeng
dc.subject.ddc004eng
dc.titleA Superresolution Framework for High-Accuracy Multiview Reconstructioneng
dc.typeINPROCEEDINGSeng
dspace.entity.typePublication
kops.citation.bibtex
@inproceedings{Goldlucke2009Super-40857,
  year={2009},
  doi={10.1007/978-3-642-03798-6_35},
  title={A Superresolution Framework for High-Accuracy Multiview Reconstruction},
  number={5748},
  isbn={978-3-642-03797-9},
  issn={0302-9743},
  publisher={Springer},
  address={Berlin},
  series={Lecture Notes in Computer Science},
  booktitle={Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings},
  pages={342--351},
  editor={Denzler, Joachim},
  author={Goldlücke, Bastian and Cremers, Daniel}
}
kops.citation.iso690GOLDLÜCKE, Bastian, Daniel CREMERS, 2009. A Superresolution Framework for High-Accuracy Multiview Reconstruction. 31st DAGM Symposium. Jena, 9. Sept. 2009 - 11. Sept. 2009. In: DENZLER, Joachim, ed. and others. Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings. Berlin: Springer, 2009, pp. 342-351. Lecture Notes in Computer Science. 5748. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-642-03797-9. Available under: doi: 10.1007/978-3-642-03798-6_35deu
kops.citation.iso690GOLDLÜCKE, Bastian, Daniel CREMERS, 2009. A Superresolution Framework for High-Accuracy Multiview Reconstruction. 31st DAGM Symposium. Jena, Sep 9, 2009 - Sep 11, 2009. In: DENZLER, Joachim, ed. and others. Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings. Berlin: Springer, 2009, pp. 342-351. Lecture Notes in Computer Science. 5748. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-642-03797-9. Available under: doi: 10.1007/978-3-642-03798-6_35eng
kops.citation.rdf
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/40857">
    <dcterms:title>A Superresolution Framework for High-Accuracy Multiview Reconstruction</dcterms:title>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dc:creator>Cremers, Daniel</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-12-06T10:20:47Z</dcterms:available>
    <dcterms:abstract xml:lang="eng">We present a variational approach to jointly estimate a displacement map and a superresolution texture for a 3D model from multiple calibrated views. The superresolution image formation model leads to an energy functional defined in terms of an integral over the object surface. This functional can be minimized by alternately solving a deblurring PDE and a total variation minimization on the surface, leading to increasingly accurate estimates of photometry and geometry, respectively. The resulting equations can be discretized and solved on texture space with the help of a conformal atlas. The superresolution approach to texture reconstruction allows to obtain fine details in the texture map which surpass individual input image resolution.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Cremers, Daniel</dc:contributor>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:issued>2009</dcterms:issued>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/40857"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-12-06T10:20:47Z</dc:date>
  </rdf:Description>
</rdf:RDF>
kops.conferencefield31st DAGM Symposium, 9. Sept. 2009 - 11. Sept. 2009, Jenadeu
kops.date.conferenceEnd2009-09-11eng
kops.date.conferenceStart2009-09-09eng
kops.flag.knbibliographyfalse
kops.location.conferenceJenaeng
kops.sourcefieldDENZLER, Joachim, ed. and others. <i>Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings</i>. Berlin: Springer, 2009, pp. 342-351. Lecture Notes in Computer Science. 5748. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-642-03797-9. Available under: doi: 10.1007/978-3-642-03798-6_35deu
kops.sourcefield.plainDENZLER, Joachim, ed. and others. Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings. Berlin: Springer, 2009, pp. 342-351. Lecture Notes in Computer Science. 5748. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-642-03797-9. Available under: doi: 10.1007/978-3-642-03798-6_35deu
kops.sourcefield.plainDENZLER, Joachim, ed. and others. Pattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedings. Berlin: Springer, 2009, pp. 342-351. Lecture Notes in Computer Science. 5748. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-642-03797-9. Available under: doi: 10.1007/978-3-642-03798-6_35eng
kops.title.conference31st DAGM Symposiumeng
relation.isAuthorOfPublicationc4ecb499-9c85-4481-832e-af061f18cbdc
relation.isAuthorOfPublication.latestForDiscoveryc4ecb499-9c85-4481-832e-af061f18cbdc
source.bibliographicInfo.fromPage342eng
source.bibliographicInfo.seriesNumber5748eng
source.bibliographicInfo.toPage351eng
source.contributor.editorDenzler, Joachim
source.flag.etalEditortrueeng
source.identifier.eissn1611-3349eng
source.identifier.isbn978-3-642-03797-9eng
source.identifier.issn0302-9743eng
source.publisherSpringereng
source.publisher.locationBerlineng
source.relation.ispartofseriesLecture Notes in Computer Scienceeng
source.titlePattern Recognition : 31st DAGM Symposium Jena, Germany, September 9-11, 2009; Proceedingseng

Dateien