IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding

Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level s...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE open journal of circuits and systems Ročník 5; s. 17 - 27
Hlavní autoři:	Sun, Yu-Han, Lee, Chiang Lo-Hsuan, Chang, Tian-Sheuan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Codecs Datasets Deep learning Discrete cosine transforms Distortion Encoding Image coding Image edge detection Image enhancement Image quality Image reconstruction just noticeable distortion Quality assessment Training data Video coding video quality assessment
ISSN:	2644-1225, 2644-1225
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41%/15% and 53%/19% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.
AbstractList	Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant information prior to compression. However, real JND cannot be well modeled with inaccurate masking equations in traditional approaches or image-level subject tests in deep learning approaches. Thus, this paper proposes a fine-grained JND prefiltering dataset guided by image quality assessment for accurate block-level JND modeling. The dataset is constructed from decoded images to include coding effects and is also perceptually enhanced with block overlap and edge preservation. Furthermore, based on this dataset, we propose a lightweight JND prefiltering network, IQNet, which can be applied directly to different quantization cases with the same model and only needs 3K parameters. The experimental results show that the proposed approach to Versatile Video Coding could yield maximum/average bitrate savings of 41%/15% and 53%/19% for all-intra and low-delay P configurations, respectively, with negligible subjective quality loss. Our method demonstrates higher perceptual quality and a model size that is an order of magnitude smaller than previous deep learning methods.
Author	Lee, Chiang Lo-Hsuan Chang, Tian-Sheuan Sun, Yu-Han
Author_xml	– sequence: 1 givenname: Yu-Han surname: Sun fullname: Sun, Yu-Han organization: Institute of Electronics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan – sequence: 2 givenname: Chiang Lo-Hsuan surname: Lee fullname: Lee, Chiang Lo-Hsuan organization: Institute of Electronics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan – sequence: 3 givenname: Tian-Sheuan orcidid: 0000-0002-0561-8745 surname: Chang fullname: Chang, Tian-Sheuan email: tschang@nycu.edu.tw organization: Institute of Electronics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
BookMark	eNpNUU1PGzEQtSoqlVL-AOJgqeek_t5dblFKaRCCohau1ng9jhxt1tTePfDvawiqOM1o5r03H-8zORrTiISccbbknHXf7q7Xq99LwYRcSqkU69QHciyMUgsuhD56l38ip6XsGGNCc85Fc0zi5v4Wpwu62cMW6f0MQ5ye6aoULGWP40Sv5ujR0-u5TPQ2TbFHcAPS7zEEzDj2SH9lDHGYMMdxS0PK9BFzgSlW1GPlJrpOvra-kI8BhoKnb_GEPPy4_LP-ubi5u9qsVzeLXupmWnRac6FZaIPooG-FAQOeg_ZCuaBBC_SOISofJIO26blxzjW9EegajibIE7I56PoEO_uU4x7ys00Q7Wsh5a2FXO8Y0OpWhhawV61SykkA07W-dSiUbhjTrmp9PWg95fR3xjLZXZrzWNe3ohOSSyOZrihxQPU5lVK_8X8qZ_bFIfvqkH1xyL45VEnnB1JExHcEabRmnfwHTaWOeQ
CODEN	IOJCC3
Cites_doi	10.1109/ICIP.2019.8803454 10.1016/j.jvcir.2017.04.009 10.1016/j.image.2023.117019 10.1109/TCSVT.2020.3030895 10.1109/TCSVT.2021.3076224 10.1016/j.ins.2023.119575 10.1109/CVPR.2012.6247954 10.1007/s11263-018-01144-2 10.1109/TCSVT.2016.2539862 10.1007/978-3-030-67070-2_3 10.1109/TCSVT.2015.2389491 10.1109/ICIP49359.2023.10222099 10.1109/TCSVT.2021.3101953 10.1109/ISCAS.2016.7539109 10.1109/ICIP.2016.7532610 10.1109/TIP.2018.2818439 10.1109/ICMEW46912.2020.9105999 10.1109/ACCESS.2020.3046194 10.1109/DCC50243.2021.00009 10.1109/CVPR46437.2021.01590 10.1109/TCSVT.2022.3163860 10.1016/j.jvcir.2023.103877 10.1109/TIP.2018.2831899 10.1109/ISPACS.2018.8923511
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SP 8FD L7M DOA
DOI	10.1109/OJCAS.2023.3344094
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	2644-1225
EndPage	27
ExternalDocumentID	oai_doaj_org_article_583f8aec48444b3aa698d8be2457005b 10_1109_OJCAS_2023_3344094 10365509
Genre	orig-research
GrantInformation_xml	– fundername: National Science and Technology Council, Taiwan grantid: 111-2622-8-A49-018-SB; 110-2221-E-A49-148-MY3; 110-2218-E-A49-015-MBK funderid: 10.13039/501100020950 – fundername: Novatek
GroupedDBID	0R~ 97E AAJGR ABAZT ABVLG ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ JAVBF M~E OCL OK1 RIA RIE AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c357t-9551250f8f29ac826a6ad1a5d24bf5a52edb0ee4df30a87c16bbb7c62eb71e6f3
IEDL.DBID	RIE
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001162376900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2644-1225
IngestDate	Fri Oct 03 12:44:25 EDT 2025 Sun Jun 29 15:58:13 EDT 2025 Sat Nov 29 05:59:26 EST 2025 Wed Aug 27 01:55:50 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by-nc-nd/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c357t-9551250f8f29ac826a6ad1a5d24bf5a52edb0ee4df30a87c16bbb7c62eb71e6f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0561-8745
OpenAccessLink	https://ieeexplore.ieee.org/document/10365509
PQID	2923136305
PQPubID	5075790
PageCount	11
ParticipantIDs	doaj_primary_oai_doaj_org_article_583f8aec48444b3aa698d8be2457005b crossref_primary_10_1109_OJCAS_2023_3344094 ieee_primary_10365509 proquest_journals_2923136305
PublicationCentury	2000
PublicationDate	20240000 2024-00-00 20240101 2024-01-01
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– year: 2024 text: 20240000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE open journal of circuits and systems
PublicationTitleAbbrev	OJCAS
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref15 ref14 ref11 ref10 ref2 ref17 ref16 ref19 ref18 Jinjian (ref1) 2018; 13 ref24 ref23 ref25 ref20 ref22 ref21 Li (ref26) 2016; 6 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref7 doi: 10.1109/ICIP.2019.8803454 – ident: ref5 doi: 10.1016/j.jvcir.2017.04.009 – ident: ref13 doi: 10.1016/j.image.2023.117019 – ident: ref23 doi: 10.1109/TCSVT.2020.3030895 – ident: ref8 doi: 10.1109/TCSVT.2021.3076224 – ident: ref11 doi: 10.1016/j.ins.2023.119575 – ident: ref22 doi: 10.1109/CVPR.2012.6247954 – ident: ref25 doi: 10.1007/s11263-018-01144-2 – ident: ref3 doi: 10.1109/TCSVT.2016.2539862 – ident: ref24 doi: 10.1007/978-3-030-67070-2_3 – ident: ref2 doi: 10.1109/TCSVT.2015.2389491 – ident: ref10 doi: 10.1109/ICIP49359.2023.10222099 – ident: ref18 doi: 10.1109/TCSVT.2021.3101953 – ident: ref19 doi: 10.1109/ISCAS.2016.7539109 – ident: ref6 doi: 10.1109/ICIP.2016.7532610 – ident: ref4 doi: 10.1109/TIP.2018.2818439 – ident: ref14 doi: 10.1109/ICMEW46912.2020.9105999 – ident: ref17 doi: 10.1109/ACCESS.2020.3046194 – volume: 6 start-page: 2 issue: 2 year: 2016 ident: ref26 article-title: Toward a practical perceptual video quality metric publication-title: Netflix Tech. Blog – ident: ref15 doi: 10.1109/DCC50243.2021.00009 – ident: ref16 doi: 10.1109/CVPR46437.2021.01590 – ident: ref9 doi: 10.1109/TCSVT.2022.3163860 – ident: ref12 doi: 10.1016/j.jvcir.2023.103877 – ident: ref21 doi: 10.1109/TIP.2018.2831899 – volume: 13 start-page: 4 year: 2018 ident: ref1 article-title: Survey of visual just noticeable difference estimation publication-title: Front. Comput. Sci. – ident: ref20 doi: 10.1109/ISPACS.2018.8923511
SSID	ssj0002511127
Score	2.2565181
Snippet	Image prefiltering with just noticeable distortion (JND) improves coding efficiency in a visual lossless way by filtering the perceptually redundant...
SourceID	doaj proquest crossref ieee
SourceType	Open Website Aggregation Database Index Database Publisher
StartPage	17
SubjectTerms	Codecs Datasets Deep learning Discrete cosine transforms Distortion Encoding Image coding Image edge detection Image enhancement Image quality Image reconstruction just noticeable distortion Quality assessment Training data Video coding video quality assessment
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYqxKEcELQglkflQ29VwPHb3JZtaelhS8VD3Cy_Iu2BXQQLEv-emSSLFnHopZccLCd2ZuLxN479fYR8hXJTB-aqqJlACTNVuSjg0ignc0jK8U5swozH9ubGnS9JfeGesI4euDPckbKisaEkaaWUUYSgnc02Fi6RmV1FjL7MuKVkCmMwAueam8UpGeaO_vweDS8OUSz8UAiJWc2bmagl7O8VVt6F5XauOd0g6z1IpMOuc5vkQ5l-ImtL1IGfyeTs77jMj-nZLQQE2jFhPNPhK88m_fk4ySVTVOui4xluccNDUvR7L4iSCj2HLk3wZzk8kAJ2pbh2Bo6CWtdw74yOZjixbZGr0x-Xo19VL5tQJaHMvHIAggDYNLbhLiRIH4IOuQ4qcxkbFRQvObJSZG4EC9akWscYTdK8RFMX3YhtsjKdTcsOodwmayKgFi0z5HEsogBgnWDYNnUxLAzIt4UJ_V3HjuHbrII53xrco8F9b_ABOUErv9ZEZuu2APzte3_7f_l7QLbQR0vNCQ1ZlhuQ_YXTfD8MHzxH-Co0xLTd_9H2HvkI7yO7FZh9sjK_fywHZDU9zScP91_aL_AFWH_cwQ priority: 102 providerName: Directory of Open Access Journals
Title	IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering for Versatile Video Coding
URI	https://ieeexplore.ieee.org/document/10365509 https://www.proquest.com/docview/2923136305 https://doaj.org/article/583f8aec48444b3aa698d8be2457005b
Volume	5
WOSCitedRecordID	wos001162376900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2644-1225 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511127 issn: 2644-1225 databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2644-1225 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511127 issn: 2644-1225 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZoxQEOPIu6UCofuKEsSfzmtiwtFImliId6s_yYSHtgg9pdJC78dmac7KoIceBiRZGdOP4y9jdjzwxjz_C-aULtqqhrQSnMVOWiwKJTTuaQlGuHZBNmsbAXF-58dFYvvjAAUA6fwZQuy15-7tOGTGUo4UIjo3Z7bM8YPThr7QwqxJWb1mwdY2r34sO7-ezTlPKDT4WQpMj8sfiUGP1jUpW_ZuKyvJze_c-O3WN3Rh7JZwPw99kNWD1gt69FF3zIlmcfF7B-yc--4ZzBh2AZP_lsF4qTv9ksM2ROCb34oqdTcORHxV-POVMS8HP8hCXtp-MDOdJbTuY1xBJrfcW2PZ_3tPYdsC-nJ5_nb6sxs0KVhDLryiFPQu7T2a51IaGGEXTITVC5lbFTQbWQYw0gcyfqYE1qdIzRJN1CNA3oTjxi-6t-BYeMtzZZE5HYaJlR1asj5QhsEkp214Cpw4Q93w65_z4E0PBF8aidLwB5AsiPAE3YK0JlV5OCX5cbONx-lCWvrOhsgCStlDKKELSz2UZoJQXrV3HCDgiia68b0Jmwoy3IfpTUK98SwxUap73H_2j2hN3CLsrB7nLE9teXG3jKbqYf6-XV5XFR4rF8_-vkuPyQvwEgB9y_
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELagIAGH8mrVhQI-cENZEj9im9t229KFEoooqDfLr0h7YFO1u0j8e2ac7KoIceASRZadOP4y9jdjzwwhr6FcVa40ha9LjinMZGE8h0srjYguSMP6ZBOqafTFhTkbnNWzL0xKKR8-S2O8zXv5sQsrNJWBhPMaGLW5Te5IIVjZu2ttTCrIlium1q4xpXn7-cN08nWMGcLHnAtUZf5YfnKU_iGtyl9zcV5gjh_-Z9ceke2BSdJJD_1jcistnpAHN-ILPiXz2ZcmLd_R2Q-YNWgfLuMXnWyCcdL3q3lMkWJKL9p0eA4OPano4ZA1JSR6Bp8wxx11eCAFgkvRwAZoQq3v0Laj0w5Xvx3y7fjofHpSDLkVisClWhYGmBKwn1a3zLgAOoarXaycjEz4VjrJUvRlSiK2vHRahar23qtQs-RVleqW75KtRbdIe4QyHbTyQG1qEUHZKz1mCawCyHZbJVW6EXmzHnJ72YfQsFn1KI3NAFkEyA4AjcgBorKpieGvcwEMtx2kyUrNW-1SEFoI4blztdFR-8QEhuuXfkR2EKIbr-vRGZH9Nch2kNVry5Dj8homvmf_aPaK3Ds5_3RqT2fNx-fkPnRX9FaYfbK1vFqlF-Ru-LmcX1-9zD_kb1ia3eA
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=IQNet%3A+Image+Quality+Assessment+Guided+Just+Noticeable+Difference+Prefiltering+for+Versatile+Video+Coding&rft.jtitle=IEEE+open+journal+of+circuits+and+systems&rft.au=Sun%2C+Yu-Han&rft.au=Lee%2C+Chiang+Lo-Hsuan&rft.au=Chang%2C+Tian-Sheuan&rft.date=2024&rft.pub=IEEE&rft.eissn=2644-1225&rft.volume=5&rft.spage=17&rft.epage=27&rft_id=info:doi/10.1109%2FOJCAS.2023.3344094&rft.externalDocID=10365509
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2644-1225&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2644-1225&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2644-1225&client=summon