Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields
Dateien
Datum
Autor:innen
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
Sammlungen
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
We present the first variational framework for multi-label segmentation on the ray space of 4D light fields. For traditional segmentation of single images, features need to be extracted from the 2D projection of a three-dimensional scene. The associated loss of geometry information can cause severe problems, for example if different objects have a very similar visual appearance. In this work, we show that using a light field instead of an image not only enables to train classifiers which can overcome many of these problems, but also provides an optimal data structure for label optimization by implicitly providing scene geometry information. It is thus possible to consistently optimize label assignment over all views simultaneously. As a further contribution, we make all light fields available online with complete depth and segmentation ground truth data where available, and thus establish the first benchmark data set for light field analysis to facilitate competitive further development of algorithms.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
WANNER, Sven, Christoph STRAEHLE, Bastian GOLDLÜCKE, 2013. Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields. CVPR 2013 : IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon, 23. Juni 2013 - 28. Juni 2013. In: PATRICK KELLENBERGER, , ed.. Proceedings : 2013 IEEE Conference on Computer Vision and Pattern Recognition ; CVPR 2013. Piscataway: IEEE, 2013, pp. 1011-1018. ISBN 978-0-7695-4989-7. Available under: doi: 10.1109/CVPR.2013.135BibTex
@inproceedings{Wanner2013Globa-29118, year={2013}, doi={10.1109/CVPR.2013.135}, title={Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields}, isbn={978-0-7695-4989-7}, publisher={IEEE}, address={Piscataway}, booktitle={Proceedings : 2013 IEEE Conference on Computer Vision and Pattern Recognition ; CVPR 2013}, pages={1011--1018}, editor={Patrick Kellenberger}, author={Wanner, Sven and Straehle, Christoph 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/123456789/29118"> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Wanner, Sven</dc:creator> <dc:contributor>Straehle, Christoph</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dcterms:issued>2013</dcterms:issued> <dcterms:title>Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields</dcterms:title> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dcterms:abstract xml:lang="eng">We present the first variational framework for multi-label segmentation on the ray space of 4D light fields. For traditional segmentation of single images, features need to be extracted from the 2D projection of a three-dimensional scene. The associated loss of geometry information can cause severe problems, for example if different objects have a very similar visual appearance. In this work, we show that using a light field instead of an image not only enables to train classifiers which can overcome many of these problems, but also provides an optimal data structure for label optimization by implicitly providing scene geometry information. It is thus possible to consistently optimize label assignment over all views simultaneously. As a further contribution, we make all light fields available online with complete depth and segmentation ground truth data where available, and thus establish the first benchmark data set for light field analysis to facilitate competitive further development of algorithms.</dcterms:abstract> <dc:contributor>Wanner, Sven</dc:contributor> <dc:contributor>Goldlücke, Bastian</dc:contributor> <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/29118"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-15T07:54:41Z</dcterms:available> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-15T07:54:41Z</dc:date> <dc:language>eng</dc:language> <dc:creator>Goldlücke, Bastian</dc:creator> <dc:creator>Straehle, Christoph</dc:creator> </rdf:Description> </rdf:RDF>