Intrinsic Light Field Decomposition and Disparity Estimation with Deep Encoder-Decoder Network

Alperovich, Anna; Johannsen, Ole; Goldlücke, Bastian

Intrinsic Light Field Decomposition and Disparity Estimation with Deep Encoder-Decoder Network

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2018

Autor:innen

Alperovich, Anna

Johannsen, Ole

Goldlücke, Bastian

Angaben zur Forschungsförderung

European Union (EU): 336978

Projekt

LIA - Light Field Imaging and Analysis

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

EUSIPCO 2018 : 26th European Signal Processing Conference. Piscataway, NJ: IEEE, 2018, pp. 2165-2169. ISBN 9789082797015

Zusammenfassung

We present an encoder-decoder deep neural network that solves non-Lambertian intrinsic light field decomposition, where we recover all three intrinsic components: albedo, shading, and specularity. We learn a sparse set of features from 3D epipolar volumes and use them in separate decoder pathways to reconstruct intrinsic light fields. While being trained on synthetic data generated with Blender, our model still generalizes to real world examples captured with a Lytro Illum plenoptic camera. The proposed method outperforms state-of-the-art approaches for single images and achieves competitive accuracy with recent modeling methods for light fields.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Decoding, Estimation, Three-dimensional displays, Convolution, Two dimensional displays, Tensile stress, Cameras

Konferenz

EUSIPCO 2018 : 26th European Signal Processing Conference, 3. Sept. 2018 - 7. Sept. 2018, Rom, Italy

Zitieren

ISO 690

ALPEROVICH, Anna, Ole JOHANNSEN, Bastian GOLDLÜCKE, 2018. Intrinsic Light Field Decomposition and Disparity Estimation with Deep Encoder-Decoder Network. EUSIPCO 2018 : 26th European Signal Processing Conference. Rom, Italy, 3. Sept. 2018 - 7. Sept. 2018. In: EUSIPCO 2018 : 26th European Signal Processing Conference. Piscataway, NJ: IEEE, 2018, pp. 2165-2169. ISBN 9789082797015

BibTex

@inproceedings{Alperovich2018-09Intri-44782,
  year={2018},
  title={Intrinsic Light Field Decomposition and Disparity Estimation with Deep Encoder-Decoder Network},
  isbn={9789082797015},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={EUSIPCO 2018 :  26th European Signal Processing Conference},
  pages={2165--2169},
  author={Alperovich, Anna and Johannsen, Ole 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/123456789/44782">
    <dc:creator>Johannsen, Ole</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-01-31T09:04:07Z</dcterms:available>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <dc:creator>Alperovich, Anna</dc:creator>
    <dcterms:abstract xml:lang="eng">We present an encoder-decoder deep neural network that solves non-Lambertian intrinsic light field decomposition, where we recover all three intrinsic components: albedo, shading, and specularity. We learn a sparse set of features from 3D epipolar volumes and use them in separate decoder pathways to reconstruct intrinsic light fields. While being trained on synthetic data generated with Blender, our model still generalizes to real world examples captured with a Lytro Illum plenoptic camera. The proposed method outperforms state-of-the-art approaches for single images and achieves competitive accuracy with recent modeling methods for light fields.</dcterms:abstract>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-01-31T09:04:07Z</dc:date>
    <dcterms:title>Intrinsic Light Field Decomposition and Disparity Estimation with Deep Encoder-Decoder Network</dcterms:title>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/44782"/>
    <dc:contributor>Johannsen, Ole</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dcterms:issued>2018-09</dcterms:issued>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja