Making Video Quality Assessment Models Robust to Bit Depth
We introduce a novel feature set, which we call HDRMAX features, that when included into Video Quality Assessment (VQA) algorithms designed for Standard Dynamic Range (SDR) videos, sensitizes them to distortions of High Dynamic Range (HDR) videos that are inadequately accounted for by these algorith...
Gespeichert in:
| Veröffentlicht in: | IEEE signal processing letters 2023-01, Vol.30, p.1-5 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 5 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE signal processing letters |
| container_volume | 30 |
| creator | Ebenezer, Joshua P. Shang, Zaixi Wu, Yongjun Wei, Hai Sethuraman, Sriram Bovik, Alan C. |
| description | We introduce a novel feature set, which we call HDRMAX features, that when included into Video Quality Assessment (VQA) algorithms designed for Standard Dynamic Range (SDR) videos, sensitizes them to distortions of High Dynamic Range (HDR) videos that are inadequately accounted for by these algorithms. While these features are not specific to HDR, and also augment the equality prediction performances of VQA models on SDR content, they are especially effective on HDR. HDRMAX features modify powerful priors drawn from Natural Video Statistics (NVS) models by enhancing their measurability where they visually impact the brightest and darkest local portions of videos, thereby capturing distortions that are often poorly accounted for by existing VQA models. As a demonstration of the efficacy of our approach, we show that, while current state-of-the-art VQA models perform poorly on 10-bit HDR databases, their performances are greatly improved by the inclusion of HDRMAX features when tested on HDR and 10-bit distorted videos. |
| doi_str_mv | 10.1109/LSP.2023.3268602 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2809879586</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10105991</ieee_id><sourcerecordid>2809879586</sourcerecordid><originalsourceid>FETCH-LOGICAL-c339t-e137cfd9eab554bb44a8852ef4db1daccffab88ffcd592733510a518d3f47b373</originalsourceid><addsrcrecordid>eNpNkDtPwzAUhS0EEqWwMzBYYk65tuPEZitvpFa8WS07uYaUti6xM_Tfk6odmO4ZvnOu9BFyymDEGOiLydvziAMXI8ELVQDfIwMmpcq4KNh-n6GETGtQh-QoxhkAKKbkgFxO7U-z_KKfTY2BvnR23qQ1HceIMS5wmeg01DiP9DW4LiaaAr1qEr3BVfo-JgfeziOe7O6QfNzdvl8_ZJOn-8fr8SSrhNApQybKytcarZMydy7PrVKSo89rx2pbVd5bp5T3VS01L4WQDKxkqhY-L50oxZCcb3dXbfjtMCYzC1277F8arkCrUktV9BRsqaoNMbbozaptFrZdGwZmY8j0hszGkNkZ6itn20qDiP9wBlJrJv4AmdVhjA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2809879586</pqid></control><display><type>article</type><title>Making Video Quality Assessment Models Robust to Bit Depth</title><source>IEEE Electronic Library (IEL)</source><creator>Ebenezer, Joshua P. ; Shang, Zaixi ; Wu, Yongjun ; Wei, Hai ; Sethuraman, Sriram ; Bovik, Alan C.</creator><creatorcontrib>Ebenezer, Joshua P. ; Shang, Zaixi ; Wu, Yongjun ; Wei, Hai ; Sethuraman, Sriram ; Bovik, Alan C.</creatorcontrib><description>We introduce a novel feature set, which we call HDRMAX features, that when included into Video Quality Assessment (VQA) algorithms designed for Standard Dynamic Range (SDR) videos, sensitizes them to distortions of High Dynamic Range (HDR) videos that are inadequately accounted for by these algorithms. While these features are not specific to HDR, and also augment the equality prediction performances of VQA models on SDR content, they are especially effective on HDR. HDRMAX features modify powerful priors drawn from Natural Video Statistics (NVS) models by enhancing their measurability where they visually impact the brightest and darkest local portions of videos, thereby capturing distortions that are often poorly accounted for by existing VQA models. As a demonstration of the efficacy of our approach, we show that, while current state-of-the-art VQA models perform poorly on 10-bit HDR databases, their performances are greatly improved by the inclusion of HDRMAX features when tested on HDR and 10-bit distorted videos.</description><identifier>ISSN: 1070-9908</identifier><identifier>EISSN: 1558-2361</identifier><identifier>DOI: 10.1109/LSP.2023.3268602</identifier><identifier>CODEN: ISPLEM</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Dynamic range ; Feature extraction ; High Dynamic Range ; Nonlinear distortion ; Prediction algorithms ; Predictive models ; Quality assessment ; Video ; Video Quality Assessment</subject><ispartof>IEEE signal processing letters, 2023-01, Vol.30, p.1-5</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c339t-e137cfd9eab554bb44a8852ef4db1daccffab88ffcd592733510a518d3f47b373</citedby><cites>FETCH-LOGICAL-c339t-e137cfd9eab554bb44a8852ef4db1daccffab88ffcd592733510a518d3f47b373</cites><orcidid>0000-0001-6067-710X ; 0000-0003-4936-9784 ; 0000-0002-4264-3130</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10105991$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10105991$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ebenezer, Joshua P.</creatorcontrib><creatorcontrib>Shang, Zaixi</creatorcontrib><creatorcontrib>Wu, Yongjun</creatorcontrib><creatorcontrib>Wei, Hai</creatorcontrib><creatorcontrib>Sethuraman, Sriram</creatorcontrib><creatorcontrib>Bovik, Alan C.</creatorcontrib><title>Making Video Quality Assessment Models Robust to Bit Depth</title><title>IEEE signal processing letters</title><addtitle>LSP</addtitle><description>We introduce a novel feature set, which we call HDRMAX features, that when included into Video Quality Assessment (VQA) algorithms designed for Standard Dynamic Range (SDR) videos, sensitizes them to distortions of High Dynamic Range (HDR) videos that are inadequately accounted for by these algorithms. While these features are not specific to HDR, and also augment the equality prediction performances of VQA models on SDR content, they are especially effective on HDR. HDRMAX features modify powerful priors drawn from Natural Video Statistics (NVS) models by enhancing their measurability where they visually impact the brightest and darkest local portions of videos, thereby capturing distortions that are often poorly accounted for by existing VQA models. As a demonstration of the efficacy of our approach, we show that, while current state-of-the-art VQA models perform poorly on 10-bit HDR databases, their performances are greatly improved by the inclusion of HDRMAX features when tested on HDR and 10-bit distorted videos.</description><subject>Algorithms</subject><subject>Dynamic range</subject><subject>Feature extraction</subject><subject>High Dynamic Range</subject><subject>Nonlinear distortion</subject><subject>Prediction algorithms</subject><subject>Predictive models</subject><subject>Quality assessment</subject><subject>Video</subject><subject>Video Quality Assessment</subject><issn>1070-9908</issn><issn>1558-2361</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkDtPwzAUhS0EEqWwMzBYYk65tuPEZitvpFa8WS07uYaUti6xM_Tfk6odmO4ZvnOu9BFyymDEGOiLydvziAMXI8ELVQDfIwMmpcq4KNh-n6GETGtQh-QoxhkAKKbkgFxO7U-z_KKfTY2BvnR23qQ1HceIMS5wmeg01DiP9DW4LiaaAr1qEr3BVfo-JgfeziOe7O6QfNzdvl8_ZJOn-8fr8SSrhNApQybKytcarZMydy7PrVKSo89rx2pbVd5bp5T3VS01L4WQDKxkqhY-L50oxZCcb3dXbfjtMCYzC1277F8arkCrUktV9BRsqaoNMbbozaptFrZdGwZmY8j0hszGkNkZ6itn20qDiP9wBlJrJv4AmdVhjA</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Ebenezer, Joshua P.</creator><creator>Shang, Zaixi</creator><creator>Wu, Yongjun</creator><creator>Wei, Hai</creator><creator>Sethuraman, Sriram</creator><creator>Bovik, Alan C.</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/0000-0001-6067-710X</orcidid><orcidid>https://orcid.org/0000-0003-4936-9784</orcidid><orcidid>https://orcid.org/0000-0002-4264-3130</orcidid></search><sort><creationdate>20230101</creationdate><title>Making Video Quality Assessment Models Robust to Bit Depth</title><author>Ebenezer, Joshua P. ; Shang, Zaixi ; Wu, Yongjun ; Wei, Hai ; Sethuraman, Sriram ; Bovik, Alan C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c339t-e137cfd9eab554bb44a8852ef4db1daccffab88ffcd592733510a518d3f47b373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Dynamic range</topic><topic>Feature extraction</topic><topic>High Dynamic Range</topic><topic>Nonlinear distortion</topic><topic>Prediction algorithms</topic><topic>Predictive models</topic><topic>Quality assessment</topic><topic>Video</topic><topic>Video Quality Assessment</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ebenezer, Joshua P.</creatorcontrib><creatorcontrib>Shang, Zaixi</creatorcontrib><creatorcontrib>Wu, Yongjun</creatorcontrib><creatorcontrib>Wei, Hai</creatorcontrib><creatorcontrib>Sethuraman, Sriram</creatorcontrib><creatorcontrib>Bovik, Alan C.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & 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 signal processing letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ebenezer, Joshua P.</au><au>Shang, Zaixi</au><au>Wu, Yongjun</au><au>Wei, Hai</au><au>Sethuraman, Sriram</au><au>Bovik, Alan C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Making Video Quality Assessment Models Robust to Bit Depth</atitle><jtitle>IEEE signal processing letters</jtitle><stitle>LSP</stitle><date>2023-01-01</date><risdate>2023</risdate><volume>30</volume><spage>1</spage><epage>5</epage><pages>1-5</pages><issn>1070-9908</issn><eissn>1558-2361</eissn><coden>ISPLEM</coden><abstract>We introduce a novel feature set, which we call HDRMAX features, that when included into Video Quality Assessment (VQA) algorithms designed for Standard Dynamic Range (SDR) videos, sensitizes them to distortions of High Dynamic Range (HDR) videos that are inadequately accounted for by these algorithms. While these features are not specific to HDR, and also augment the equality prediction performances of VQA models on SDR content, they are especially effective on HDR. HDRMAX features modify powerful priors drawn from Natural Video Statistics (NVS) models by enhancing their measurability where they visually impact the brightest and darkest local portions of videos, thereby capturing distortions that are often poorly accounted for by existing VQA models. As a demonstration of the efficacy of our approach, we show that, while current state-of-the-art VQA models perform poorly on 10-bit HDR databases, their performances are greatly improved by the inclusion of HDRMAX features when tested on HDR and 10-bit distorted videos.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/LSP.2023.3268602</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0001-6067-710X</orcidid><orcidid>https://orcid.org/0000-0003-4936-9784</orcidid><orcidid>https://orcid.org/0000-0002-4264-3130</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1070-9908 |
| ispartof | IEEE signal processing letters, 2023-01, Vol.30, p.1-5 |
| issn | 1070-9908 1558-2361 |
| language | eng |
| recordid | cdi_proquest_journals_2809879586 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Dynamic range Feature extraction High Dynamic Range Nonlinear distortion Prediction algorithms Predictive models Quality assessment Video Video Quality Assessment |
| title | Making Video Quality Assessment Models Robust to Bit Depth |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T14%3A53%3A33IST&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=Making%20Video%20Quality%20Assessment%20Models%20Robust%20to%20Bit%20Depth&rft.jtitle=IEEE%20signal%20processing%20letters&rft.au=Ebenezer,%20Joshua%20P.&rft.date=2023-01-01&rft.volume=30&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.issn=1070-9908&rft.eissn=1558-2361&rft.coden=ISPLEM&rft_id=info:doi/10.1109/LSP.2023.3268602&rft_dat=%3Cproquest_RIE%3E2809879586%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=2809879586&rft_id=info:pmid/&rft_ieee_id=10105991&rfr_iscdi=true |