Publikation: Spatial and Angular Variational Super-Resolution of 4D Light Fields
Lade...
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2012
Autor:innen
Wanner, Sven
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
FITZGIBBON, Andrew, ed.. Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V. Berlin: Springer, 2012, pp. 608-621. Lecture notes in computer science. 7576. ISBN 978-3-642-33714-7. Available under: doi: 10.1007/978-3-642-33715-4_44
Zusammenfassung
We present a variational framework to generate super-resolved novel views from 4D light field data sampled at low resolution, for example by a plenoptic camera. In contrast to previous work, we formulate the problem of view synthesis as a continuous inverse problem, which allows us to correctly take into account foreshortening effects caused by scene geometry transformations. High-accuracy depth maps for the input views are locally estimated using epipolar plane image analysis, which yields floating point depth precision without the need for expensive matching cost minimization. The disparity maps are further improved by increasing angular resolution with synthesized intermediate views. Minimization of the super-resolution model energy is performed with state of the art convex optimization algorithms within seconds.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Image Processing and Computer Vision, Pattern Recognition, Artificial Intelligence (incl. Robotics), Computer Graphics, Algorithm Analysis and Problem Complexity, Computer Imaging, Vision, Pattern Recognition and Graphics
Konferenz
12th European Conference on Computer Vision, 7. Okt. 2012 - 13. Okt. 2012, Florenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
WANNER, Sven, Bastian GOLDLÜCKE, 2012. Spatial and Angular Variational Super-Resolution of 4D Light Fields. 12th European Conference on Computer Vision. Florenz, 7. Okt. 2012 - 13. Okt. 2012. In: FITZGIBBON, Andrew, ed.. Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V. Berlin: Springer, 2012, pp. 608-621. Lecture notes in computer science. 7576. ISBN 978-3-642-33714-7. Available under: doi: 10.1007/978-3-642-33715-4_44BibTex
@inproceedings{Wanner2012Spati-29095,
year={2012},
doi={10.1007/978-3-642-33715-4_44},
title={Spatial and Angular Variational Super-Resolution of 4D Light Fields},
number={7576},
isbn={978-3-642-33714-7},
publisher={Springer},
address={Berlin},
series={Lecture notes in computer science},
booktitle={Computer Vision – ECCV 2012 : 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V},
pages={608--621},
editor={Fitzgibbon, Andrew},
author={Wanner, Sven 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/123456789/29095">
<dcterms:issued>2012</dcterms:issued>
<dcterms:abstract xml:lang="eng">We present a variational framework to generate super-resolved novel views from 4D light field data sampled at low resolution, for example by a plenoptic camera. In contrast to previous work, we formulate the problem of view synthesis as a continuous inverse problem, which allows us to correctly take into account foreshortening effects caused by scene geometry transformations. High-accuracy depth maps for the input views are locally estimated using epipolar plane image analysis, which yields floating point depth precision without the need for expensive matching cost minimization. The disparity maps are further improved by increasing angular resolution with synthesized intermediate views. Minimization of the super-resolution model energy is performed with state of the art convex optimization algorithms within seconds.</dcterms:abstract>
<dc:contributor>Goldlücke, Bastian</dc:contributor>
<dc:creator>Goldlücke, Bastian</dc:creator>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-08T09:38:46Z</dc:date>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-08T09:38:46Z</dcterms:available>
<dc:language>eng</dc:language>
<dc:contributor>Wanner, Sven</dc:contributor>
<dcterms:title>Spatial and Angular Variational Super-Resolution of 4D Light Fields</dcterms:title>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/29095"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Wanner, Sven</dc:creator>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
