Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric

Arbitrary neural style transfer is a vital topic with great research value and wide industrial application, which strives to render the structure of one image using the style of another. Recent researches have devoted great efforts on the task of arbitrary style transfer (AST) for improving the styl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on circuits and systems for video technology 2023-07, Vol.33 (7), p.3055-3070
Hauptverfasser: Chen, Hangwei, Shao, Feng, Chai, Xiongli, Gu, Yuese, Jiang, Qiuping, Meng, Xiangchao, Ho, Yo-Sung
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3070
container_issue 7
container_start_page 3055
container_title IEEE transactions on circuits and systems for video technology
container_volume 33
creator Chen, Hangwei
Shao, Feng
Chai, Xiongli
Gu, Yuese
Jiang, Qiuping
Meng, Xiangchao
Ho, Yo-Sung
description Arbitrary neural style transfer is a vital topic with great research value and wide industrial application, which strives to render the structure of one image using the style of another. Recent researches have devoted great efforts on the task of arbitrary style transfer (AST) for improving the stylization quality. However, there are very few explorations about the quality evaluation of AST images, even it can potentially guide the design of different algorithms. In this paper, we first construct a new AST images quality assessment database (AST-IQAD), which consists 150 content-style image pairs and the corresponding 1200 stylized images produced by eight typical AST algorithms. Then, a subjective study is conducted on our AST-IQAD database, which obtains the subjective rating scores of all stylized images on the three subjective evaluations, i.e., content preservation (CP), style resemblance (SR), and overall vision (OV). To quantitatively measure the quality of AST image, we propose a new sparse representation-based method, which computes the quality according to the sparse feature similarity. Experimental results on our AST-IQAD have demonstrated the superiority of the proposed method. The dataset and source code will be released at https://github.com/Hangwei-Chen/AST-IQAD-SRQE
doi_str_mv 10.1109/TCSVT.2022.3231041
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2831521536</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9994780</ieee_id><sourcerecordid>2831521536</sourcerecordid><originalsourceid>FETCH-LOGICAL-c295t-ecbc663a78ab7c4c0d887d5a4ce2930f1e380d737c85e7000d9757b849d1b65e3</originalsourceid><addsrcrecordid>eNo9kN9LwzAQx4MoOKf_gL4EfO68JE2T-jbG_AGTIet8DWl6hY7azjQd9L-3c7KnO-6-3zu-H0LuGcwYg_QpW2y-shkHzmeCCwYxuyATJqWOOAd5OfYgWaQ5k9fkput2ACzWsZqQ7Wdv6yoMdHmwdW9D1Ta0Lenc51Xw1g90E4YaaeZt05Xon-mmz3foQnXAcdUXA7VNQdfn2QcGX7lbclXausO7_zol25dltniLVuvX98V8FTmeyhChy12SCKu0zZWLHRRaq0La2CFPBZQMhYZCCeW0RAUARaqkynWcFixPJIopeTzd3fv2p8cumF3b-2Z8abgWTI55RTKq-EnlfNt1Hkuz99X3GM4wMEd85g-fOeIz__hG08PJVCHi2ZCmaaw0iF-gYmwB</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2831521536</pqid></control><display><type>article</type><title>Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric</title><source>IEEE/IET Electronic Library (IEL)</source><creator>Chen, Hangwei ; Shao, Feng ; Chai, Xiongli ; Gu, Yuese ; Jiang, Qiuping ; Meng, Xiangchao ; Ho, Yo-Sung</creator><creatorcontrib>Chen, Hangwei ; Shao, Feng ; Chai, Xiongli ; Gu, Yuese ; Jiang, Qiuping ; Meng, Xiangchao ; Ho, Yo-Sung</creatorcontrib><description>Arbitrary neural style transfer is a vital topic with great research value and wide industrial application, which strives to render the structure of one image using the style of another. Recent researches have devoted great efforts on the task of arbitrary style transfer (AST) for improving the stylization quality. However, there are very few explorations about the quality evaluation of AST images, even it can potentially guide the design of different algorithms. In this paper, we first construct a new AST images quality assessment database (AST-IQAD), which consists 150 content-style image pairs and the corresponding 1200 stylized images produced by eight typical AST algorithms. Then, a subjective study is conducted on our AST-IQAD database, which obtains the subjective rating scores of all stylized images on the three subjective evaluations, i.e., content preservation (CP), style resemblance (SR), and overall vision (OV). To quantitatively measure the quality of AST image, we propose a new sparse representation-based method, which computes the quality according to the sparse feature similarity. Experimental results on our AST-IQAD have demonstrated the superiority of the proposed method. The dataset and source code will be released at https://github.com/Hangwei-Chen/AST-IQAD-SRQE</description><identifier>ISSN: 1051-8215</identifier><identifier>EISSN: 1558-2205</identifier><identifier>DOI: 10.1109/TCSVT.2022.3231041</identifier><identifier>CODEN: ITCTEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Arbitrary style transfer (AST) ; content preservation (CP) ; Image quality ; image quality assessment (IQA) ; Industrial applications ; Measurement ; Neural networks ; overall vision (OV) ; Q-factor ; Quality assessment ; Source code ; sparse coding ; sparse feature similarity ; style resemblance (SR) ; Task analysis</subject><ispartof>IEEE transactions on circuits and systems for video technology, 2023-07, Vol.33 (7), p.3055-3070</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c295t-ecbc663a78ab7c4c0d887d5a4ce2930f1e380d737c85e7000d9757b849d1b65e3</citedby><cites>FETCH-LOGICAL-c295t-ecbc663a78ab7c4c0d887d5a4ce2930f1e380d737c85e7000d9757b849d1b65e3</cites><orcidid>0000-0002-6025-9343 ; 0000-0002-2495-9924 ; 0000-0002-4245-5391 ; 0000-0002-7220-1034 ; 0000-0002-3756-2029 ; 0000-0002-7405-3143</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9994780$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9994780$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chen, Hangwei</creatorcontrib><creatorcontrib>Shao, Feng</creatorcontrib><creatorcontrib>Chai, Xiongli</creatorcontrib><creatorcontrib>Gu, Yuese</creatorcontrib><creatorcontrib>Jiang, Qiuping</creatorcontrib><creatorcontrib>Meng, Xiangchao</creatorcontrib><creatorcontrib>Ho, Yo-Sung</creatorcontrib><title>Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric</title><title>IEEE transactions on circuits and systems for video technology</title><addtitle>TCSVT</addtitle><description>Arbitrary neural style transfer is a vital topic with great research value and wide industrial application, which strives to render the structure of one image using the style of another. Recent researches have devoted great efforts on the task of arbitrary style transfer (AST) for improving the stylization quality. However, there are very few explorations about the quality evaluation of AST images, even it can potentially guide the design of different algorithms. In this paper, we first construct a new AST images quality assessment database (AST-IQAD), which consists 150 content-style image pairs and the corresponding 1200 stylized images produced by eight typical AST algorithms. Then, a subjective study is conducted on our AST-IQAD database, which obtains the subjective rating scores of all stylized images on the three subjective evaluations, i.e., content preservation (CP), style resemblance (SR), and overall vision (OV). To quantitatively measure the quality of AST image, we propose a new sparse representation-based method, which computes the quality according to the sparse feature similarity. Experimental results on our AST-IQAD have demonstrated the superiority of the proposed method. The dataset and source code will be released at https://github.com/Hangwei-Chen/AST-IQAD-SRQE</description><subject>Algorithms</subject><subject>Arbitrary style transfer (AST)</subject><subject>content preservation (CP)</subject><subject>Image quality</subject><subject>image quality assessment (IQA)</subject><subject>Industrial applications</subject><subject>Measurement</subject><subject>Neural networks</subject><subject>overall vision (OV)</subject><subject>Q-factor</subject><subject>Quality assessment</subject><subject>Source code</subject><subject>sparse coding</subject><subject>sparse feature similarity</subject><subject>style resemblance (SR)</subject><subject>Task analysis</subject><issn>1051-8215</issn><issn>1558-2205</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kN9LwzAQx4MoOKf_gL4EfO68JE2T-jbG_AGTIet8DWl6hY7azjQd9L-3c7KnO-6-3zu-H0LuGcwYg_QpW2y-shkHzmeCCwYxuyATJqWOOAd5OfYgWaQ5k9fkput2ACzWsZqQ7Wdv6yoMdHmwdW9D1Ta0Lenc51Xw1g90E4YaaeZt05Xon-mmz3foQnXAcdUXA7VNQdfn2QcGX7lbclXausO7_zol25dltniLVuvX98V8FTmeyhChy12SCKu0zZWLHRRaq0La2CFPBZQMhYZCCeW0RAUARaqkynWcFixPJIopeTzd3fv2p8cumF3b-2Z8abgWTI55RTKq-EnlfNt1Hkuz99X3GM4wMEd85g-fOeIz__hG08PJVCHi2ZCmaaw0iF-gYmwB</recordid><startdate>20230701</startdate><enddate>20230701</enddate><creator>Chen, Hangwei</creator><creator>Shao, Feng</creator><creator>Chai, Xiongli</creator><creator>Gu, Yuese</creator><creator>Jiang, Qiuping</creator><creator>Meng, Xiangchao</creator><creator>Ho, Yo-Sung</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-6025-9343</orcidid><orcidid>https://orcid.org/0000-0002-2495-9924</orcidid><orcidid>https://orcid.org/0000-0002-4245-5391</orcidid><orcidid>https://orcid.org/0000-0002-7220-1034</orcidid><orcidid>https://orcid.org/0000-0002-3756-2029</orcidid><orcidid>https://orcid.org/0000-0002-7405-3143</orcidid></search><sort><creationdate>20230701</creationdate><title>Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric</title><author>Chen, Hangwei ; Shao, Feng ; Chai, Xiongli ; Gu, Yuese ; Jiang, Qiuping ; Meng, Xiangchao ; Ho, Yo-Sung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c295t-ecbc663a78ab7c4c0d887d5a4ce2930f1e380d737c85e7000d9757b849d1b65e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Arbitrary style transfer (AST)</topic><topic>content preservation (CP)</topic><topic>Image quality</topic><topic>image quality assessment (IQA)</topic><topic>Industrial applications</topic><topic>Measurement</topic><topic>Neural networks</topic><topic>overall vision (OV)</topic><topic>Q-factor</topic><topic>Quality assessment</topic><topic>Source code</topic><topic>sparse coding</topic><topic>sparse feature similarity</topic><topic>style resemblance (SR)</topic><topic>Task analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Hangwei</creatorcontrib><creatorcontrib>Shao, Feng</creatorcontrib><creatorcontrib>Chai, Xiongli</creatorcontrib><creatorcontrib>Gu, Yuese</creatorcontrib><creatorcontrib>Jiang, Qiuping</creatorcontrib><creatorcontrib>Meng, Xiangchao</creatorcontrib><creatorcontrib>Ho, Yo-Sung</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on circuits and systems for video technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Hangwei</au><au>Shao, Feng</au><au>Chai, Xiongli</au><au>Gu, Yuese</au><au>Jiang, Qiuping</au><au>Meng, Xiangchao</au><au>Ho, Yo-Sung</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric</atitle><jtitle>IEEE transactions on circuits and systems for video technology</jtitle><stitle>TCSVT</stitle><date>2023-07-01</date><risdate>2023</risdate><volume>33</volume><issue>7</issue><spage>3055</spage><epage>3070</epage><pages>3055-3070</pages><issn>1051-8215</issn><eissn>1558-2205</eissn><coden>ITCTEM</coden><abstract>Arbitrary neural style transfer is a vital topic with great research value and wide industrial application, which strives to render the structure of one image using the style of another. Recent researches have devoted great efforts on the task of arbitrary style transfer (AST) for improving the stylization quality. However, there are very few explorations about the quality evaluation of AST images, even it can potentially guide the design of different algorithms. In this paper, we first construct a new AST images quality assessment database (AST-IQAD), which consists 150 content-style image pairs and the corresponding 1200 stylized images produced by eight typical AST algorithms. Then, a subjective study is conducted on our AST-IQAD database, which obtains the subjective rating scores of all stylized images on the three subjective evaluations, i.e., content preservation (CP), style resemblance (SR), and overall vision (OV). To quantitatively measure the quality of AST image, we propose a new sparse representation-based method, which computes the quality according to the sparse feature similarity. Experimental results on our AST-IQAD have demonstrated the superiority of the proposed method. The dataset and source code will be released at https://github.com/Hangwei-Chen/AST-IQAD-SRQE</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TCSVT.2022.3231041</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-6025-9343</orcidid><orcidid>https://orcid.org/0000-0002-2495-9924</orcidid><orcidid>https://orcid.org/0000-0002-4245-5391</orcidid><orcidid>https://orcid.org/0000-0002-7220-1034</orcidid><orcidid>https://orcid.org/0000-0002-3756-2029</orcidid><orcidid>https://orcid.org/0000-0002-7405-3143</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1051-8215
ispartof IEEE transactions on circuits and systems for video technology, 2023-07, Vol.33 (7), p.3055-3070
issn 1051-8215
1558-2205
language eng
recordid cdi_proquest_journals_2831521536
source IEEE/IET Electronic Library (IEL)
subjects Algorithms
Arbitrary style transfer (AST)
content preservation (CP)
Image quality
image quality assessment (IQA)
Industrial applications
Measurement
Neural networks
overall vision (OV)
Q-factor
Quality assessment
Source code
sparse coding
sparse feature similarity
style resemblance (SR)
Task analysis
title Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T16%3A16%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Quality%20Evaluation%20of%20Arbitrary%20Style%20Transfer:%20Subjective%20Study%20and%20Objective%20Metric&rft.jtitle=IEEE%20transactions%20on%20circuits%20and%20systems%20for%20video%20technology&rft.au=Chen,%20Hangwei&rft.date=2023-07-01&rft.volume=33&rft.issue=7&rft.spage=3055&rft.epage=3070&rft.pages=3055-3070&rft.issn=1051-8215&rft.eissn=1558-2205&rft.coden=ITCTEM&rft_id=info:doi/10.1109/TCSVT.2022.3231041&rft_dat=%3Cproquest_RIE%3E2831521536%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2831521536&rft_id=info:pmid/&rft_ieee_id=9994780&rfr_iscdi=true