Light Field Intrinsics With a Deep Encoder-Decoder Network

Lade...
Vorschaubild
Dateien
Alperovich_2-12v0m36c2ik507.pdf
Alperovich_2-12v0m36c2ik507.pdfGröße: 2.98 MBDownloads: 502
Datum
2018
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
European Union (EU): 336978
Projekt
LIA - Light Field Imaging and Analysis
Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
2018 IEEE Conference on Computer Vision and Pattern Recognition. The Computer Vision Foundation, 2018, pp. 9145-9154. Available under: doi: 10.1109/CVPR.2018.00953
Zusammenfassung

We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers. The complex structure of the light field is thus reduced to a comparatively low-dimensional representation, which can be decoded in a variety of ways. The different pathways of upconvolution we currently support are for disparity estimation and separation of the lightfield into diffuse and specular intrinsic components. The key idea is that we can jointly perform unsupervised training for the autoencoder path of the network, and supervised training for the other decoders. This way, we find features which are both tailored to the respective tasks and generalize well to datasets for which only example light fields are available. We provide an extensive evaluation on synthetic light field data, and show that the network yields good results on previously unseen real world data captured by a Lytro Illum camera and various gantries.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
CVPR 2018 : IEEE Conference on Computer Vision and Pattern Recognition, 18. Juni 2018 - 22. Juni 2018, Salt Lake City, Utah
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690ALPEROVICH, Anna, Ole JOHANNSEN, Michael STRECKE, Bastian GOLDLÜCKE, 2018. Light Field Intrinsics With a Deep Encoder-Decoder Network. CVPR 2018 : IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, Utah, 18. Juni 2018 - 22. Juni 2018. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition. The Computer Vision Foundation, 2018, pp. 9145-9154. Available under: doi: 10.1109/CVPR.2018.00953
BibTex
@inproceedings{Alperovich2018Light-44382,
  year={2018},
  doi={10.1109/CVPR.2018.00953},
  title={Light Field Intrinsics With a Deep Encoder-Decoder Network},
  url={http://openaccess.thecvf.com/content_cvpr_2018/html/Alperovich_Light_Field_Intrinsics_CVPR_2018_paper.html},
  publisher={The Computer Vision Foundation},
  booktitle={2018 IEEE Conference on Computer Vision and Pattern Recognition},
  pages={9145--9154},
  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/123456789/44382">
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Alperovich, Anna</dc:creator>
    <dc:contributor>Strecke, Michael</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Strecke, Michael</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/44382/1/Alperovich_2-12v0m36c2ik507.pdf"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/44382/1/Alperovich_2-12v0m36c2ik507.pdf"/>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:abstract xml:lang="eng">We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers. The complex structure of the light field is thus reduced to a comparatively low-dimensional representation, which can be decoded in a variety of ways. The different pathways of upconvolution we currently support are for disparity estimation and separation of the lightfield into diffuse and specular intrinsic components. The key idea is that we can jointly perform unsupervised training for the autoencoder path of the network, and supervised training for the other decoders. This way, we find features which are both tailored to the respective tasks and generalize well to datasets for which only example light fields are available. We provide an extensive evaluation on synthetic light field data, and show that the network yields good results on previously unseen real world data captured by a Lytro Illum camera and various gantries.</dcterms:abstract>
    <dcterms:title>Light Field Intrinsics With a Deep Encoder-Decoder Network</dcterms:title>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-12-19T13:13:36Z</dc:date>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2018-12-19T13:13:36Z</dcterms:available>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <dcterms:issued>2018</dcterms:issued>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/44382"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <dc:creator>Johannsen, Ole</dc:creator>
    <dc:language>eng</dc:language>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen