Variational and Deep Learning Approaches for Intrinsic Light Field Decomposition

Lade...
Vorschaubild
Dateien
Alperovich_2-ee236e5qzmf94.pdf
Alperovich_2-ee236e5qzmf94.pdfGröße: 7.52 MBDownloads: 786
Datum
2020
Autor:innen
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Dissertation
Publikationsstatus
Published
Erschienen in
Zusammenfassung

Intrinsic image decomposition aims to separate an illumination invariant reflectance image from an input color image, which is still one of the fundamental problems in computer vision. This decomposition is widely used in photo and material editing, image segmentation and shape estimation tasks. According to the dichromatic reflection model, the light reflected from a scene point has two independent components: light reflected from the surface body and light at the interface. Body reflection is known as the diffuse component and it is independent of viewing direction, while interface reflection is known as the specular component and it is view-dependent. Most intrinsic image algorithms are designed for Lambertian scenes, with only diffuse reflection. However, their performance decreases if a scene contains specularity. In the real world, there are few scenes with only Lambertian objects. Instead, they have specular surfaces, which makes the decomposition problem harder due to the complicated nature of specular reflection. This thesis focuses on intrinsic light field decomposition, where we formulate and solve the problem with respect to three variables: albedo, shading, and specularity. Thus, we can deal with non-Lambertian scenes. We use a 4D light field, which is a collection of images sampled on a regular grid, instead of a single image. Rich information inherited from the light field allows us to distinguish between diffuse and specular reflection, and also allows us to robustly recover the intrinsic components. We tackle the problem with variational and deep learning approaches, compare their performance, and discuss the strengths and weaknesses of both techniques. In the variational method, we introduce priors for the intrinsic components and we solve an energy minimization problem with convex optimization. Because geometrical information plays an important role in the appearance and behavior of intrinsic components, we develop a disparity estimation method, where we not only optimize the disparity labels but also enforce piecewise smoothness of a normal map. Our deep learning approach is based on the assumption that if mathematical models allow us to compute a disparity and intrinsic components from a light field, then these models can be approximated with a deep convolutional neural network. Moreover, because disparity estimation and intrinsic light fields are closely related, a single network can be sufficient to perform all tasks together and they can benefit from each other. Thus, we establish a multi-task learning strategy for light fields, which is not only limited to the particular collection of tasks but (in theory) can also be used for various computer vision applications. We demonstrate the advantage of our approach on four state-of-the-art computer vision problems: disparity estimation, reflection separation, intrinsic images, and super-resolution. Extensive evaluations based on multiple, publicly-available, synthetic and real-world datasets prove our methodology and show the advantage of using light fields over other data structures. Our proposed algorithms outperform state-of-the-art methods for intrinsic images and disparity estimation, and achieve a competing quality for super-resolution and reflection separation.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690ALPEROVICH, Anna, 2020. Variational and Deep Learning Approaches for Intrinsic Light Field Decomposition [Dissertation]. Konstanz: University of Konstanz
BibTex
@phdthesis{Alperovich2020Varia-49781,
  year={2020},
  title={Variational and Deep Learning Approaches for Intrinsic Light Field Decomposition},
  author={Alperovich, Anna},
  address={Konstanz},
  school={Universität Konstanz}
}
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/123456789/49781">
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-06-03T07:10:36Z</dc:date>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:abstract xml:lang="eng">Intrinsic image decomposition aims to separate an illumination invariant reflectance image from an input color image, which is still one of the fundamental problems in computer vision. This decomposition is widely used in photo and material editing, image segmentation and shape estimation tasks. According to the dichromatic reflection model, the light reflected from a scene point has two independent components: light reflected from the surface body and light at the interface. Body reflection is known as the diffuse component and it is independent of viewing direction, while interface reflection is known as the specular component and it is view-dependent. Most intrinsic image algorithms are designed for Lambertian scenes, with only diffuse reflection. However, their performance decreases if a scene contains specularity. In the real world, there are few scenes with only Lambertian objects. Instead, they have specular surfaces, which makes the decomposition problem harder due to the complicated nature of specular reflection. This thesis focuses on intrinsic light field decomposition, where we formulate and solve the problem with respect to three variables: albedo, shading, and specularity. Thus, we can deal with non-Lambertian scenes. We use a 4D light field, which is a collection of images sampled on a regular grid, instead of a single image. Rich information inherited from the light field allows us to distinguish between diffuse and specular reflection, and also allows us to robustly recover the intrinsic components. We tackle the problem with variational and deep learning approaches, compare their performance, and discuss the strengths and weaknesses of both techniques. In the variational method, we introduce priors for the intrinsic components and we solve an energy minimization problem with convex optimization. Because geometrical information plays an important role in the appearance and behavior of intrinsic components, we develop a disparity estimation method, where we not only optimize the disparity labels but also enforce piecewise smoothness of a normal map. Our deep learning approach is based on the assumption that if mathematical models allow us to compute a disparity and intrinsic components from a light field, then these models can be approximated with a deep convolutional neural network. Moreover, because disparity estimation and intrinsic light fields are closely related, a single network can be sufficient to perform all tasks together and they can benefit from each other. Thus, we establish a multi-task learning strategy for light fields, which is not only limited to the particular collection of tasks but (in theory) can also be used for various computer vision applications. We demonstrate the advantage of our approach on four state-of-the-art computer vision problems: disparity estimation, reflection separation, intrinsic images, and super-resolution. Extensive evaluations based on multiple, publicly-available, synthetic and real-world datasets prove our methodology and show the advantage of using light fields over other data structures. Our proposed algorithms outperform state-of-the-art methods for intrinsic images and disparity estimation, and achieve a competing quality for super-resolution and reflection separation.</dcterms:abstract>
    <dc:language>eng</dc:language>
    <dcterms:title>Variational and Deep Learning Approaches for Intrinsic Light Field Decomposition</dcterms:title>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49781/3/Alperovich_2-ee236e5qzmf94.pdf"/>
    <dc:creator>Alperovich, Anna</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:issued>2020</dcterms:issued>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/49781/3/Alperovich_2-ee236e5qzmf94.pdf"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-06-03T07:10:36Z</dcterms:available>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/49781"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
February 19, 2020
Hochschulschriftenvermerk
Konstanz, Univ., Diss., 2020
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Begutachtet
Diese Publikation teilen