Type of Publication: | Contribution to a conference |
Author: | Aubry, Mathieu; Kolev, Kalin; Goldlücke, Bastian; Cremers, Daniel |
Year of publication: | 2011 |
Conference: | IEE International Conference on Computer Vision, Nov 3, 2011 - Nov 13, 2011, Barcelona |
Published in: | IEEE International Conference on Computer Vision (ICCV), 2011 : 6 - 13 Nov. 2011, Barcelona, Spain. - Piscataway : IEEE, 2011. - pp. 1411-1418. - ISBN 978-1-4577-1101-5 |
DOI (citable link): | https://dx.doi.org/10.1109/ICCV.2011.6126396 |
Summary: |
We introduce a spatially dense variational approach to estimate the calibration of multiple cameras in the context of 3D reconstruction. We propose a relaxation scheme which allows to transform the original photometric error into a geometric one, thereby decoupling the problems of dense matching and camera calibration. In both quantitative and qualitative experiments, we demonstrate that the proposed decoupling scheme allows for robust and accurate estimation of camera parameters. In particular, the presented dense camera calibration formulation leads to substantial improvements both in the reconstructed 3D geometry and in the super-resolution texture estimation.
|
Subject (DDC): | 004 Computer Science |
Keywords: | calibration, cameras, geometry, image matching, image reconstruction, image resolution, image texture, photometry |
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
AUBRY, Mathieu, Kalin KOLEV, Bastian GOLDLÜCKE, Daniel CREMERS, 2011. Decoupling Photometry and Geometry in Dense Variational Camera Calibration. IEE International Conference on Computer Vision. Barcelona, Nov 3, 2011 - Nov 13, 2011. In: IEEE International Conference on Computer Vision (ICCV), 2011 : 6 - 13 Nov. 2011, Barcelona, Spain. Piscataway:IEEE, pp. 1411-1418. ISBN 978-1-4577-1101-5. Available under: doi: 10.1109/ICCV.2011.6126396
@inproceedings{Aubry2011Decou-29094, title={Decoupling Photometry and Geometry in Dense Variational Camera Calibration}, year={2011}, doi={10.1109/ICCV.2011.6126396}, isbn={978-1-4577-1101-5}, address={Piscataway}, publisher={IEEE}, booktitle={IEEE International Conference on Computer Vision (ICCV), 2011 : 6 - 13 Nov. 2011, Barcelona, Spain}, pages={1411--1418}, author={Aubry, Mathieu and Kolev, Kalin and Goldlücke, Bastian and Cremers, Daniel} }
<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/rdf/resource/123456789/29094"> <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/29094"/> <dcterms:issued>2011</dcterms:issued> <dc:creator>Goldlücke, Bastian</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-08T09:35:40Z</dcterms:available> <dc:contributor>Aubry, Mathieu</dc:contributor> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-08T09:35:40Z</dc:date> <dc:contributor>Kolev, Kalin</dc:contributor> <dc:creator>Aubry, Mathieu</dc:creator> <dc:creator>Kolev, Kalin</dc:creator> <dc:contributor>Goldlücke, Bastian</dc:contributor> <dcterms:title>Decoupling Photometry and Geometry in Dense Variational Camera Calibration</dcterms:title> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:abstract xml:lang="eng">We introduce a spatially dense variational approach to estimate the calibration of multiple cameras in the context of 3D reconstruction. We propose a relaxation scheme which allows to transform the original photometric error into a geometric one, thereby decoupling the problems of dense matching and camera calibration. In both quantitative and qualitative experiments, we demonstrate that the proposed decoupling scheme allows for robust and accurate estimation of camera parameters. In particular, the presented dense camera calibration formulation leads to substantial improvements both in the reconstructed 3D geometry and in the super-resolution texture estimation.</dcterms:abstract> <dc:contributor>Cremers, Daniel</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:creator>Cremers, Daniel</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:language>eng</dc:language> </rdf:Description> </rdf:RDF>