Publikation: Recovery of geometry, natural illumination, and BRDF from a single light field image
Lade...
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2022
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
Journal of the Optical Society of America A. Optica Publishing Group. 2022, 39(1), pp. 72-85. ISSN 1084-7529. eISSN 1520-8532. Available under: doi: 10.1364/JOSAA.433491
Zusammenfassung
We propose an inverse rendering model for light fields to recover surface normals, depth, reflectance, and natural illumination. Our setting is fully uncalibrated, with the reflectance modeled with a spatially constant Blinn–Phong bidirectional reflectance distribution function (BRDF) and illumination as an environment map. While previous work makes strong assumptions in this difficult scenario, focusing solely on specific types of objects such as faces or imposing very strong priors, our approach leverages only the light field structure, where a solution consistent across all subaperture views is sought. The optimization is based primarily on shading, which is sensitive to fine geometric details that are propagated to the initial coarse depth map. Despite the problem being inherently ill posed, we achieve encouraging results on synthetic as well as real-world data.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
SULC, Antonin, Ole JOHANNSEN, Bastian GOLDLÜCKE, 2022. Recovery of geometry, natural illumination, and BRDF from a single light field image. In: Journal of the Optical Society of America A. Optica Publishing Group. 2022, 39(1), pp. 72-85. ISSN 1084-7529. eISSN 1520-8532. Available under: doi: 10.1364/JOSAA.433491BibTex
@article{Sulc2022Recov-56128,
year={2022},
doi={10.1364/JOSAA.433491},
title={Recovery of geometry, natural illumination, and BRDF from a single light field image},
number={1},
volume={39},
issn={1084-7529},
journal={Journal of the Optical Society of America A},
pages={72--85},
author={Sulc, Antonin 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/123456789/56128">
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-01-14T12:34:36Z</dcterms:available>
<dc:contributor>Goldlücke, Bastian</dc:contributor>
<dcterms:issued>2022</dcterms:issued>
<dc:language>eng</dc:language>
<dcterms:title>Recovery of geometry, natural illumination, and BRDF from a single light field image</dcterms:title>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dc:creator>Johannsen, Ole</dc:creator>
<bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/56128"/>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:contributor>Sulc, Antonin</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:contributor>Johannsen, Ole</dc:contributor>
<dcterms:abstract xml:lang="eng">We propose an inverse rendering model for light fields to recover surface normals, depth, reflectance, and natural illumination. Our setting is fully uncalibrated, with the reflectance modeled with a spatially constant Blinn–Phong bidirectional reflectance distribution function (BRDF) and illumination as an environment map. While previous work makes strong assumptions in this difficult scenario, focusing solely on specific types of objects such as faces or imposing very strong priors, our approach leverages only the light field structure, where a solution consistent across all subaperture views is sought. The optimization is based primarily on shading, which is sensitive to fine geometric details that are propagated to the initial coarse depth map. Despite the problem being inherently ill posed, we achieve encouraging results on synthetic as well as real-world data.</dcterms:abstract>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Sulc, Antonin</dc:creator>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-01-14T12:34:36Z</dc:date>
<dc:creator>Goldlücke, Bastian</dc:creator>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
