Globally Consistent Depth Labeling of 4D Lightfields

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

WANNER, Sven, Bastian GOLDLÜCKE, 2012. Globally Consistent Depth Labeling of 4D Lightfields. Conference on Computer Vision and Pattern Recognition. Providence, RI, Jun 16, 2012 - Jun 21, 2012. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 : 16 - 21 June 2012, Providence, RI, USA. Piscataway:IEEE, pp. 41-48. ISBN 978-1-4673-1226-4. Available under: doi: 10.1109/CVPR.2012.6247656

@inproceedings{Wanner2012Globa-29096, title={Globally Consistent Depth Labeling of 4D Lightfields}, year={2012}, doi={10.1109/CVPR.2012.6247656}, isbn={978-1-4673-1226-4}, address={Piscataway}, publisher={IEEE}, booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 : 16 - 21 June 2012, Providence, RI, USA}, pages={41--48}, author={Wanner, Sven and Goldlücke, Bastian} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:date rdf:datatype="">2014-10-08T09:54:03Z</dc:date> <dcterms:available rdf:datatype="">2014-10-08T09:54:03Z</dcterms:available> <bibo:uri rdf:resource=""/> <dcterms:issued>2012</dcterms:issued> <dc:creator>Wanner, Sven</dc:creator> <dc:creator>Goldlücke, Bastian</dc:creator> <dc:language>eng</dc:language> <dc:contributor>Goldlücke, Bastian</dc:contributor> <dcterms:title>Globally Consistent Depth Labeling of 4D Lightfields</dcterms:title> <dc:contributor>Wanner, Sven</dc:contributor> <dcterms:abstract xml:lang="eng">We present a novel paradigm to deal with depth reconstruction from 4D light fields in a variational framework. Taking into account the special structure of light field data, we reformulate the problem of stereo matching to a constrained labeling problem on epipolar plane images, which can be thought of as vertical and horizontal 2D cuts through the field. This alternative formulation allows to estimate accurate depth values even for specular surfaces, while simultaneously taking into account global visibility constraints in order to obtain consistent depth maps for all views. The resulting optimization problems are solved with state-of-the-art convex relaxation techniques. We test our algorithm on a number of synthetic and real-world examples captured with a light field gantry and a plenoptic camera, and compare to ground truth where available. All data sets as well as source code are provided online for additional evaluation.</dcterms:abstract> <dspace:isPartOfCollection rdf:resource=""/> <dcterms:isPartOf rdf:resource=""/> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


My Account