Shadow and Specularity Priors for Intrinsic Light Field Decomposition

PELILLO, Marcello, ed., Edwin HANCOCK, ed.. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition EMMCVPR 2017: Energy Minimization Methods in Computer Vision and Pattern Recognition. Cham: Springer, 2018, pp. 389-406. Lecture Notes in Computer Science. 10746. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_26

Zusammenfassung

In this work, we focus on the problem of intrinsic scene decomposition in light fields. Our main contribution is a novel prior to cope with cast shadows and inter-reflections. In contrast to other approaches which model inter-reflection based only on geometry, we model indirect shading by combining geometric and color information. We compute a shadow confidence measure for the light field and use it in the regularization constraints. Another contribution is an improved specularity estimation by using color information from sub-aperture views. The new priors are embedded in a recent framework to decompose the input light field into albedo, shading, and specularity. We arrive at a variational model where we regularize albedo and the two shading components on epipolar plane images, encouraging them to be consistent across all sub-aperture views. Our method is evaluated on ground truth synthetic datasets and real world light fields. We outperform both state-of-the art approaches for RGB+D images and recent methods proposed for light fields.

Fachgebiet (DDC)

004 Informatik

Konferenz

11th International Conference, EMMCVPR 2017, 30. Okt. 2017 - 1. Nov. 2017, Venice, Italy

Zitieren

ISO 690

ALPEROVICH, Anna, Ole JOHANNSEN, Michael STRECKE, Bastian GOLDLÜCKE, 2018. Shadow and Specularity Priors for Intrinsic Light Field Decomposition. 11th International Conference, EMMCVPR 2017. Venice, Italy, 30. Okt. 2017 - 1. Nov. 2017. In: PELILLO, Marcello, ed., Edwin HANCOCK, ed.. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition EMMCVPR 2017: Energy Minimization Methods in Computer Vision and Pattern Recognition. Cham: Springer, 2018, pp. 389-406. Lecture Notes in Computer Science. 10746. ISBN 978-3-319-78198-3. Available under: doi: 10.1007/978-3-319-78199-0_26

BibTex

@inproceedings{Alperovich2018Shado-42891,
  year={2018},
  doi={10.1007/978-3-319-78199-0_26},
  title={Shadow and Specularity Priors for Intrinsic Light Field Decomposition},
  number={10746},
  isbn={978-3-319-78198-3},
  publisher={Springer},
  address={Cham},
  series={Lecture Notes in Computer Science},
  booktitle={International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition  EMMCVPR 2017: Energy Minimization Methods in Computer Vision and Pattern Recognition},
  pages={389--406},
  editor={Pelillo, Marcello and Hancock, Edwin},
  author={Alperovich, Anna and Johannsen, Ole and Strecke, Michael and Goldlücke, Bastian}
}

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/123456789/42891">
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-07-20T08:16:45Z</dcterms:available>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:issued>2018</dcterms:issued>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Johannsen, Ole</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/42891"/>
    <dc:creator>Alperovich, Anna</dc:creator>
    <dc:language>eng</dc:language>
    <dc:creator>Strecke, Michael</dc:creator>
    <dcterms:title>Shadow and Specularity Priors for Intrinsic Light Field Decomposition</dcterms:title>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:contributor>Strecke, Michael</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-07-20T08:16:45Z</dc:date>
    <dcterms:abstract xml:lang="eng">In this work, we focus on the problem of intrinsic scene decomposition in light fields. Our main contribution is a novel prior to cope with cast shadows and inter-reflections. In contrast to other approaches which model inter-reflection based only on geometry, we model indirect shading by combining geometric and color information. We compute a shadow confidence measure for the light field and use it in the regularization constraints. Another contribution is an improved specularity estimation by using color information from sub-aperture views. The new priors are embedded in a recent framework to decompose the input light field into albedo, shading, and specularity. We arrive at a variational model where we regularize albedo and the two shading components on epipolar plane images, encouraging them to be consistent across all sub-aperture views. Our method is evaluated on ground truth synthetic datasets and real world light fields. We outperform both state-of-the art approaches for RGB+D images and recent methods proposed for light fields.</dcterms:abstract>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja