Technical Report on Visual Quality Assessment for Frame Interpolation

Men, Hui; Lin, Hanhe; Hosu, Vlad; Maurer, Daniel; Bruhn, Andrés; Saupe, Dietmar

Technical Report on Visual Quality Assessment for Frame Interpolation

Dateien

Men_2-10m8w9fa5jo522.pdfGröße: 7.05 MBDownloads: 151

Datum

2019

Autor:innen

Men, Hui

Lin, Hanhe

Hosu, Vlad

Maurer, Daniel

Bruhn, Andrés

Saupe, Dietmar

Publikationstyp

Preprint

Publikationsstatus

Published

Zusammenfassung

Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpolated frames, based on these predictions, with the correct frames from the actual image sequences. For the latter comparisons, objective measures such as mean square errors are applied. However, for applications like image interpolation, the expected user's quality of experience cannot be fully deduced from such simple quality measures. Therefore, we conducted a subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark. We used paired comparisons with forced choice and reconstructed absolute quality scale values according to Thurstone's model using the classical least squares method. The results give rise to a re-ranking of 141 participating algorithms w.r.t. visual quality of interpolated frames mostly based on optical flow estimation. Our re-ranking result shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

MEN, Hui, Hanhe LIN, Vlad HOSU, Daniel MAURER, Andrés BRUHN, Dietmar SAUPE, 2019. Technical Report on Visual Quality Assessment for Frame Interpolation

BibTex

@unpublished{Men2019-01-16T16:11:39ZTechn-44825,
  year={2019},
  title={Technical Report on Visual Quality Assessment for Frame Interpolation},
  author={Men, Hui and Lin, Hanhe and Hosu, Vlad and Maurer, Daniel and Bruhn, Andrés and Saupe, Dietmar}
}

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/123456789/44825">
    <dc:contributor>Saupe, Dietmar</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-04T14:08:16Z</dcterms:available>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dcterms:title>Technical Report on Visual Quality Assessment for Frame Interpolation</dcterms:title>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Hosu, Vlad</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-04T14:08:16Z</dc:date>
    <dc:creator>Maurer, Daniel</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/44825/3/Men_2-10m8w9fa5jo522.pdf"/>
    <dcterms:issued>2019-01-16T16:11:39Z</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:abstract xml:lang="eng">Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpolated frames, based on these predictions, with the correct frames from the actual image sequences. For the latter comparisons, objective measures such as mean square errors are applied. However, for applications like image interpolation, the expected user's quality of experience cannot be fully deduced from such simple quality measures. Therefore, we conducted a subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark. We used paired comparisons with forced choice and reconstructed absolute quality scale values according to Thurstone's model using the classical least squares method. The results give rise to a re-ranking of 141 participating algorithms w.r.t. visual quality of interpolated frames mostly based on optical flow estimation. Our re-ranking result shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.</dcterms:abstract>
    <dc:contributor>Hosu, Vlad</dc:contributor>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dc:language>eng</dc:language>
    <dc:creator>Bruhn, Andrés</dc:creator>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/44825/3/Men_2-10m8w9fa5jo522.pdf"/>
    <dc:contributor>Bruhn, Andrés</dc:contributor>
    <dc:contributor>Men, Hui</dc:contributor>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/44825"/>
    <dc:contributor>Maurer, Daniel</dc:contributor>
    <dc:creator>Men, Hui</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja