Epipolar Plane Image Refocusing for Improved Depth Estimation and Occlusion Handling

Diebold, Maximilian; Goldlücke, Bastian

Epipolar Plane Image Refocusing for Improved Depth Estimation and Occlusion Handling

Files

There are no files associated with this item.

Date

2013

Authors

Diebold, Maximilian

Goldlücke, Bastian

DOI (citable link)

10.2312/PE.VMV.VMV13.145-152

Collections

Informatik und Informationswissenschaft

Publication type

Contribution to a conference collection

Published in

VMV 2013 : Vision Modeling and Visualization / Dieter Fellner (ed.). - Goslar : Eurographics Association, 2013. - pp. 145-152. - ISBN 978-3-905674-51-4

Abstract

In contrast to traditional imaging, the higher dimensionality of a light field offers directional information about the captured intensity. This information can be leveraged to estimate the disparity of 3D points in the captured scene. A recent approach to estimate disparities analyzes the structure tensor and evaluates the orientation on epipolar plane images (EPIs). While the resulting disparity maps are generally satisfying, the allowed disparity range is small and occlusion boundaries can become smeared and noisy. In this paper, we first introduce an approach to extend the total allowed disparity range. This allows for example the investigation of camera setups with a larger baseline, like in the Middlebury 3D light fields. Second, we introduce a method to handle the difficulties arising at boundaries between fore- and background objects to achieve sharper edge transitions.

Subject (DDC)

004 Computer Science

Conference

Annual Workshop on Vision, Modeling and Visualization : VMV, Sep 11, 2013 - Sep 13, 2013, Lugano

Cite This

ISO 690

DIEBOLD, Maximilian, Bastian GOLDLÜCKE, 2013. Epipolar Plane Image Refocusing for Improved Depth Estimation and Occlusion Handling. Annual Workshop on Vision, Modeling and Visualization : VMV. Lugano, Sep 11, 2013 - Sep 13, 2013. In: DIETER FELLNER, , ed.. VMV 2013 : Vision Modeling and Visualization. Goslar:Eurographics Association, pp. 145-152. ISBN 978-3-905674-51-4. Available under: doi: 10.2312/PE.VMV.VMV13.145-152

BibTex

@inproceedings{Diebold2013Epipo-29115,
  year={2013},
  doi={10.2312/PE.VMV.VMV13.145-152},
  title={Epipolar Plane Image Refocusing for Improved Depth Estimation and Occlusion Handling},
  isbn={978-3-905674-51-4},
  publisher={Eurographics Association},
  address={Goslar},
  booktitle={VMV 2013 : Vision Modeling and Visualization},
  pages={145--152},
  editor={Dieter Fellner},
  author={Diebold, Maximilian 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/123456789/29115">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-15T06:25:13Z</dc:date>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-10-15T06:25:13Z</dcterms:available>
    <dcterms:title>Epipolar Plane Image Refocusing for Improved Depth Estimation and Occlusion Handling</dcterms:title>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/29115"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:creator>Diebold, Maximilian</dc:creator>
    <dcterms:abstract xml:lang="eng">In contrast to traditional imaging, the higher dimensionality of a light field offers directional information about the captured intensity. This information can be leveraged to estimate the disparity of 3D points in the captured scene. A recent approach to estimate disparities analyzes the structure tensor and evaluates the orientation on epipolar plane images (EPIs). While the resulting disparity maps are generally satisfying, the allowed disparity range is small and occlusion boundaries can become smeared and noisy. In this paper, we first introduce an approach to extend the total allowed disparity range. This allows for example the investigation of camera setups with a larger baseline, like in the Middlebury 3D light fields. Second, we introduce a method to handle the difficulties arising at boundaries between fore- and background objects to achieve sharper edge transitions.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Diebold, Maximilian</dc:contributor>
    <dc:language>eng</dc:language>
    <dcterms:issued>2013</dcterms:issued>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

No