KonIQ++ : Boosting No-Reference Image Quality Assessment in the Wild by Jointly Predicting Image Quality and Defects

No Thumbnail Available
Files
There are no files associated with this item.
Date
2021
Authors
Su, Shaolin
Zhang, Yanning
Editors
Contact
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
URI (citable link)
DOI (citable link)
ArXiv-ID
International patent number
Link to the license
EU project number
Project
Open Access publication
Restricted until
Title in another language
Research Projects
Organizational Units
Journal Issue
Publication type
Contribution to a conference collection
Publication status
Published
Published in
The British Machine Vision Conference (BMVC). - pp. 1-12
Abstract
Although image quality assessment (IQA) in-the-wild has been researched in computer vision, it is still challenging to precisely estimate perceptual image quality in the presence of real-world complex and composite distortions. In order to improve machine learning solutions for IQA, we consider side information denoting the presence of distortions besides the basic quality ratings in IQA datasets. Specifically, we extend one of the largest in-the-wild IQA databases, KonIQ-10k, to KonIQ++, by collecting distortion annotations for each image, aiming to improve quality prediction together with distortion identification. We further explore the interactions between image quality and distortion by proposing a novel IQA model, which jointly predicts image quality and distortion by recurrently refining task-specific features in a multi-stage fusion framework. Our dataset KonIQ++, along with the model, boosts IQA performance and generalization ability, demonstrating its potential for solving the challenging authentic IQA task. The proposed model can also accurately predict distinct image defects, suggesting its application in image processing tasks such as image colorization and deblurring.
Summary in another language
Subject (DDC)
004 Computer Science
Keywords
Conference
The 32nd British Machine Vision Conference, Nov 22, 2021 - Nov 25, 2021, Online
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690SU, Shaolin, Vlad HOSU, Hanhe LIN, Yanning ZHANG, Dietmar SAUPE, 2021. KonIQ++ : Boosting No-Reference Image Quality Assessment in the Wild by Jointly Predicting Image Quality and Defects. The 32nd British Machine Vision Conference. Online, Nov 22, 2021 - Nov 25, 2021. In: The British Machine Vision Conference (BMVC), pp. 1-12
BibTex
@inproceedings{Su2021KonIQ-56990,
  year={2021},
  title={KonIQ++ : Boosting No-Reference Image Quality Assessment in the Wild by Jointly Predicting Image Quality and Defects},
  url={https://www.bmvc2021-virtualconference.com/conference/papers/paper_0868.html},
  booktitle={The British Machine Vision Conference (BMVC)},
  pages={1--12},
  author={Su, Shaolin and Hosu, Vlad and Lin, Hanhe and Zhang, Yanning 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/123456789/56990">
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <dc:creator>Zhang, Yanning</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-03-24T15:08:44Z</dcterms:available>
    <dc:rights>terms-of-use</dc:rights>
    <dc:language>eng</dc:language>
    <dc:creator>Su, Shaolin</dc:creator>
    <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"/>
    <dcterms:abstract xml:lang="eng">Although image quality assessment (IQA) in-the-wild has been researched in computer vision, it is still challenging to precisely estimate perceptual image quality in the presence of real-world complex and composite distortions. In order to improve machine learning solutions for IQA, we consider side information denoting the presence of distortions besides the basic quality ratings in IQA datasets. Specifically, we extend one of the largest in-the-wild IQA databases, KonIQ-10k, to KonIQ++, by collecting distortion annotations for each image, aiming to improve quality prediction together with distortion identification. We further explore the interactions between image quality and distortion by proposing a novel IQA model, which jointly predicts image quality and distortion by recurrently refining task-specific features in a multi-stage fusion framework. Our dataset KonIQ++, along with the model, boosts IQA performance and generalization ability, demonstrating its potential for solving the challenging authentic IQA task. The proposed model can also accurately predict distinct image defects, suggesting its application in image processing tasks such as image colorization and deblurring.</dcterms:abstract>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Su, Shaolin</dc:contributor>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dc:contributor>Zhang, Yanning</dc:contributor>
    <dcterms:title>KonIQ++ : Boosting No-Reference Image Quality Assessment in the Wild by Jointly Predicting Image Quality and Defects</dcterms:title>
    <dcterms:issued>2021</dcterms:issued>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/56990"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-03-24T15:08:44Z</dc:date>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Hosu, Vlad</dc:contributor>
    <dc:creator>Hosu, Vlad</dc:creator>
  </rdf:Description>
</rdf:RDF>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Contact
Test date of URL
2022-01-19
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
Yes
Refereed