A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields

Zitieren

Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

HONAUER, Katrin, Ole JOHANNSEN, Daniel KONDERMANN, Bastian GOLDLÜCKE, 2017. A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields. 13th Asian Conference on Computer Vision. Taipei, 20. Nov 2016 - 24. Nov 2016. In: LAI, Shang-Hong, ed. and others. Computer Vision - ACCV 2016 : 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part III. 13th Asian Conference on Computer Vision. Taipei, 20. Nov 2016 - 24. Nov 2016. Cham:Springer, pp. 19-34. ISSN 0302-9743. eISSN 1611-3349. ISBN 978-3-319-54186-0

@inproceedings{Honauer2017-03-11Datas-38021, title={A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields}, year={2017}, doi={10.1007/978-3-319-54187-7_2}, number={10113}, isbn={978-3-319-54186-0}, issn={0302-9743}, address={Cham}, publisher={Springer}, series={Lecture Notes in Computer Science}, booktitle={Computer Vision - ACCV 2016 : 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part III}, pages={19--34}, editor={Lai, Shang-Hong}, author={Honauer, Katrin and Johannsen, Ole and Kondermann, Daniel 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/123456789/38021"> <dcterms:title>A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields</dcterms:title> <dc:contributor>Johannsen, Ole</dc:contributor> <dc:creator>Johannsen, Ole</dc:creator> <dcterms:issued>2017-03-11</dcterms:issued> <dc:creator>Goldlücke, Bastian</dc:creator> <dcterms:abstract xml:lang="eng">In computer vision communities such as stereo, optical flow, or visual tracking, commonly accepted and widely used benchmarks have enabled objective comparison and boosted scientific progress. In the emergent light field community, a comparable benchmark and evaluation methodology is still missing. The performance of newly proposed methods is often demonstrated qualitatively on a handful of images, making quantitative comparison and targeted progress very difficult. To overcome these difficulties, we propose a novel light field benchmark. We provide 24 carefully designed synthetic, densely sampled 4D light fields with highly accurate disparity ground truth. We thoroughly evaluate four state-of-the-art light field algorithms and one multi-view stereo algorithm using existing and novel error measures. This consolidated state-of-the art may serve as a baseline to stimulate and guide further scientific progress. We publish the benchmark website http://www.lightfield-analysis.net, an evaluation toolkit, and our rendering setup to encourage submissions of both algorithms and further datasets.</dcterms:abstract> <dc:contributor>Honauer, Katrin</dc:contributor> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-03-17T07:00:09Z</dc:date> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2017-03-17T07:00:09Z</dcterms:available> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/38021"/> <dc:language>eng</dc:language> <dc:creator>Kondermann, Daniel</dc:creator> <dc:contributor>Goldlücke, Bastian</dc:contributor> <dc:creator>Honauer, Katrin</dc:creator> <dc:contributor>Kondermann, Daniel</dc:contributor> </rdf:Description> </rdf:RDF>

Das Dokument erscheint in:

KOPS Suche


Stöbern

Mein Benutzerkonto