Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2017
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
European Union (EU): 336978
Projekt
LIA - Light Field Imaging and Analysis
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
O'CONNER, Lisa, ed.. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017, pp. 2529-2537. IEEE Xplore Digital Library. ISSN 1063-6919. ISBN 978-1-5386-0457-1. Available under: doi: 10.1109/CVPR.2017.271
Zusammenfassung

We introduce a novel approach to jointly estimate consistent depth and normal maps from 4D light fields, with two main contributions. First, we build a cost volume from focal stack symmetry. However, in contrast to previous approaches, we introduce partial focal stacks in order to be able to robustly deal with occlusions. This idea already yields significanly better disparity maps. Second, even recent sublabel-accurate methods for multi-label optimization recover only a piecewise flat disparity map from the cost volume, with normals pointing mostly towards the image plane. This renders normal maps recovered from these approaches unsuitable for potential subsequent applications. We therefore propose regularization with a novel prior linking depth to normals, and imposing smoothness of the resulting normal field. We then jointly optimize over depth and normals to achieve estimates for both which surpass previous work in accuracy on a recent benchmark.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21. Juli 2017 - 26. Juli 2017, Honolulu, HI
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690STRECKE, Michael, Anna ALPEROVICH, Bastian GOLDLÜCKE, 2017. Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, 21. Juli 2017 - 26. Juli 2017. In: O'CONNER, Lisa, ed.. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017, pp. 2529-2537. IEEE Xplore Digital Library. ISSN 1063-6919. ISBN 978-1-5386-0457-1. Available under: doi: 10.1109/CVPR.2017.271
BibTex
@inproceedings{Strecke2017Accur-41705,
  year={2017},
  doi={10.1109/CVPR.2017.271},
  title={Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry},
  isbn={978-1-5386-0457-1},
  issn={1063-6919},
  publisher={IEEE},
  address={Piscataway, NJ},
  series={IEEE Xplore Digital Library},
  booktitle={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages={2529--2537},
  editor={O'Conner, Lisa},
  author={Strecke, Michael and Alperovich, Anna 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/123456789/41705">
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:abstract xml:lang="eng">We introduce a novel approach to jointly estimate consistent depth and normal maps from 4D light fields, with two main contributions. First, we build a cost volume from focal stack symmetry. However, in contrast to previous approaches, we introduce partial focal stacks in order to be able to robustly deal with occlusions. This idea already yields significanly better disparity maps. Second, even recent sublabel-accurate methods for multi-label optimization recover only a piecewise flat disparity map from the cost volume, with normals pointing mostly towards the image plane. This renders normal maps recovered from these approaches unsuitable for potential subsequent applications. We therefore propose regularization with a novel prior linking depth to normals, and imposing smoothness of the resulting normal field. We then jointly optimize over depth and normals to achieve estimates for both which surpass previous work in accuracy on a recent benchmark.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Alperovich, Anna</dc:creator>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/41705"/>
    <dcterms:title>Accurate Depth and Normal Maps from Occlusion-Aware Focal Stack Symmetry</dcterms:title>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:creator>Strecke, Michael</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-03-07T09:35:57Z</dc:date>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-03-07T09:35:57Z</dcterms:available>
    <dc:language>eng</dc:language>
    <dc:contributor>Strecke, Michael</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2017</dcterms:issued>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen