Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

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. Jun 2013 - 28. Jun 2013. In: PATRICK KELLENBERGER, , ed.. Proceedings : 2013 IEEE Conference on Computer Vision and Pattern Recognition ; CVPR 2013. CVPR 2013 : IEEE Conference on Computer Vision and Pattern Recognition. Portland, Oregon, 23. Jun 2013 - 28. Jun 2013. Piscataway:IEEE, pp. 1011-1018. ISBN 978-0-7695-4989-7

@inproceedings{Wanner2013Globa-29118, title={Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields}, year={2013}, doi={10.1109/CVPR.2013.135}, isbn={978-0-7695-4989-7}, address={Piscataway}, publisher={IEEE}, 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 xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/29118"> <dcterms:title>Globally Consistent Multi-Label Assignment on the Ray Space of {4D}Light Fields</dcterms:title> <dc:contributor>Straehle, Christoph</dc:contributor> <dc:contributor>Wanner, Sven</dc:contributor> <dc:contributor>Goldlücke, Bastian</dc:contributor> <dcterms:issued>2013</dcterms:issued> <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:creator>Goldlücke, Bastian</dc:creator> <dc:creator>Straehle, Christoph</dc:creator> <dc:language>eng</dc:language> <dc:creator>Wanner, Sven</dc:creator> <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> </rdf:Description> </rdf:RDF>

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto