Inverse Lightfield Rendering for Shape, Reflection and Natural Illumination

dc.contributor.authorSulc, Antonin
dc.contributor.authorJohannsen, Ole
dc.contributor.authorGoldlücke, Bastian
dc.date.accessioned2018-06-29T09:58:41Z
dc.date.available2018-06-29T09:58:41Z
dc.date.issued2018eng
dc.description.abstractWe propose an inverse rendering model for light fields to recover surface normals, depth, reflectance and natural illumination. Our setting is fully uncalibrated, with the reflectance modeled with a spatially-constant Blinn-Phong model and illumination as an environment map. While previous work makes strong assumptions in this difficult scenario, focusing solely on specific types of objects like faces or imposing very strong priors, our approach leverages only the light field structure, where a solution consistent across all subaperture views is sought. The optimization is based primarily on shading, which is sensitive to fine geometric details which are propagated to the initial coarse depth map. Despite the problem being inherently ill-posed, we achieve encouraging results on synthetic as well as real-world data.eng
dc.description.versionpublishedeng
dc.identifier.doi10.1007/978-3-319-78199-0_25eng
dc.identifier.urihttps://kops.uni-konstanz.de/handle/123456789/42738
dc.language.isoengeng
dc.subject.ddc004eng
dc.titleInverse Lightfield Rendering for Shape, Reflection and Natural Illuminationeng
dc.typeINPROCEEDINGSeng
dspace.entity.typePublication
kops.citation.bibtex
@inproceedings{Sulc2018Inver-42738,
  year={2018},
  doi={10.1007/978-3-319-78199-0_25},
  title={Inverse Lightfield Rendering for Shape, Reflection and Natural Illumination},
  number={10746},
  isbn={978-3-319-78198-3},
  issn={0302-9743},
  publisher={Springer},
  address={Cham},
  series={Lecture Notes in Computer Science},
  booktitle={Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers},
  pages={372--388},
  editor={Pelillo, Marcello and Hancock, Edwin},
  author={Sulc, Antonin and Johannsen, Ole and Goldlücke, Bastian}
}
kops.citation.iso690SULC, Antonin, Ole JOHANNSEN, Bastian GOLDLÜCKE, 2018. Inverse Lightfield Rendering for Shape, Reflection and Natural Illumination. 11th International Conference, EMMCVPR 2017. Venice, Italy, 30. Okt. 2017 - 1. Nov. 2017. In: PELILLO, Marcello, ed., Edwin HANCOCK, ed.. Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers. Cham: Springer, 2018, pp. 372-388. Lecture Notes in Computer Science. 10746. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_25deu
kops.citation.iso690SULC, Antonin, Ole JOHANNSEN, Bastian GOLDLÜCKE, 2018. Inverse Lightfield Rendering for Shape, Reflection and Natural Illumination. 11th International Conference, EMMCVPR 2017. Venice, Italy, Oct 30, 2017 - Nov 1, 2017. In: PELILLO, Marcello, ed., Edwin HANCOCK, ed.. Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers. Cham: Springer, 2018, pp. 372-388. Lecture Notes in Computer Science. 10746. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_25eng
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/123456789/42738">
    <dcterms:title>Inverse Lightfield Rendering for Shape, Reflection and Natural Illumination</dcterms:title>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-06-29T09:58:41Z</dcterms:available>
    <dc:contributor>Sulc, Antonin</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-06-29T09:58:41Z</dc:date>
    <dc:creator>Sulc, Antonin</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Johannsen, Ole</dc:creator>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2018</dcterms:issued>
    <dc:language>eng</dc:language>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/42738"/>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <dcterms:abstract xml:lang="eng">We propose an inverse rendering model for light fields to recover surface normals, depth, reflectance and natural illumination. Our setting is fully uncalibrated, with the reflectance modeled with a spatially-constant Blinn-Phong model and illumination as an environment map. While previous work makes strong assumptions in this difficult scenario, focusing solely on specific types of objects like faces or imposing very strong priors, our approach leverages only the light field structure, where a solution consistent across all subaperture views is sought. The optimization is based primarily on shading, which is sensitive to fine geometric details which are propagated to the initial coarse depth map. Despite the problem being inherently ill-posed, we achieve encouraging results on synthetic as well as real-world data.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </rdf:Description>
</rdf:RDF>
kops.conferencefield11th International Conference, EMMCVPR 2017, 30. Okt. 2017 - 1. Nov. 2017, Venice, Italydeu
kops.date.conferenceEnd2017-11-01eng
kops.date.conferenceStart2017-10-30eng
kops.description.funding{"first": "eu", "second": "336978"}
kops.flag.knbibliographytrue
kops.location.conferenceVenice, Italyeng
kops.relation.euProjectID336978
kops.relation.uniknProjectTitleLIA - Light Field Imaging and Analysis
kops.sourcefieldPELILLO, Marcello, ed., Edwin HANCOCK, ed.. <i>Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers</i>. Cham: Springer, 2018, pp. 372-388. Lecture Notes in Computer Science. 10746. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_25deu
kops.sourcefield.plainPELILLO, Marcello, ed., Edwin HANCOCK, ed.. Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers. Cham: Springer, 2018, pp. 372-388. Lecture Notes in Computer Science. 10746. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_25deu
kops.sourcefield.plainPELILLO, Marcello, ed., Edwin HANCOCK, ed.. Energy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected papers. Cham: Springer, 2018, pp. 372-388. Lecture Notes in Computer Science. 10746. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_25eng
kops.title.conference11th International Conference, EMMCVPR 2017eng
relation.isAuthorOfPublication1374fb01-c7c5-430a-a31b-fb5c645601d6
relation.isAuthorOfPublication8a9774c6-456a-4f6e-965d-daa28c6e3d58
relation.isAuthorOfPublicationc4ecb499-9c85-4481-832e-af061f18cbdc
relation.isAuthorOfPublication.latestForDiscovery1374fb01-c7c5-430a-a31b-fb5c645601d6
source.bibliographicInfo.fromPage372eng
source.bibliographicInfo.seriesNumber10746eng
source.bibliographicInfo.toPage388eng
source.contributor.editorPelillo, Marcello
source.contributor.editorHancock, Edwin
source.identifier.eissn1611-3349eng
source.identifier.isbn978-3-319-78198-3eng
source.identifier.issn0302-9743eng
source.publisherSpringereng
source.publisher.locationChameng
source.relation.ispartofseriesLecture Notes in Computer Scienceeng
source.titleEnergy Minimization Methods in Computer Vision and Pattern Recognition : 11th International Conference, EMMCVPR 2017, Venice, Italy, October 30 - November 1, 2017, revised selected paperseng

Dateien