Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset

Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on multimedia Vol. 26; pp. 10816 - 10827
Main Authors Lin, Liqun, Wang, Mingxing, Yang, Jing, Zhang, Keke, Zhao, Tiesong
Format Journal Article
LanguageEnglish
Published IEEE 2024
Subjects
Distortion
Encoding
Image coding
Perceivable encoding artifact
Quality assessment
Video compression
video compression artifact removal
video quality assessment
Online AccessGet full text

Cover

Abstract Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.
AbstractList Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.
Author Yang, Jing
Wang, Mingxing
Zhao, Tiesong
Zhang, Keke
Lin, Liqun
Author_xml – sequence: 1
  givenname: Liqun
  orcidid: 0000-0002-5900-4175
  surname: Lin
  fullname: Lin, Liqun
  email: lin_liqun@fzu.edu.cn
  organization: Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
– sequence: 2
  givenname: Mingxing
  orcidid: 0009-0003-3748-3763
  surname: Wang
  fullname: Wang, Mingxing
  email: 221127191@fzu.edu.cn
  organization: Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
– sequence: 3
  givenname: Jing
  surname: Yang
  fullname: Yang, Jing
  email: 201127079@fzu.edu.cn
  organization: Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
– sequence: 4
  givenname: Keke
  orcidid: 0000-0002-9789-6151
  surname: Zhang
  fullname: Zhang, Keke
  email: 201110007@fzu.edu.cn
  organization: Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
– sequence: 5
  givenname: Tiesong
  orcidid: 0000-0002-7497-8883
  surname: Zhao
  fullname: Zhao, Tiesong
  email: t.zhao@fzu.edu.cn
  organization: Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, College of Physics and Information Engineering, Fuzhou University, Fuzhou, China
BookMark eNp9kE1LAzEQhoNUsK3ePXjIH9g6ySabxltt6we0CFJ7XbLZCUbb3ZIExX_vLvUgHjzNMLzPMPOMyKBpGyTkksGEMdDXm_V6woGLSS6YkEKfkCHTgmUASg26XnLINGdwRkYxvgF0IVBDst20nybUdOmctx6bRLe-xpbO2_0hYIy-begsJO-MTXSBCW3qR6ap6TPu2w-zu6EzeouNfd2b8E4XJpmI6ZycOrOLePFTx-TlbrmZP2Srp_vH-WyVWV6IlBUKmbVW8ZzlEnBaQyUdMCeZ66ZOTEErUXGprSwcskqomleocqEZ5xrrfEyK414b2hgDutL6ZPoTUzB-VzIoeztlZ6fs7ZQ_djoQ_oCH4LsPvv5Dro6IR8RfcTkVOZ_m3-TGcek
CODEN ITMUF8
CitedBy_id crossref_primary_10_1109_ACCESS_2025_3542824
Cites_doi 10.1109/TCSVT.2022.3227039
10.1109/WACV48630.2021.00164
10.1007/s11760-019-01543-z
10.3390/s21196429
10.1109/ACSSC.2003.1292216
10.1109/ICCV.2015.73
10.1109/VCIP49819.2020.9301847
10.1109/TBC.2022.3208426
10.1109/TMM.2022.3214775
10.1109/ICPR.2010.579
10.1109/TIP.2015.2502725
10.1109/TIP.2018.2889276
10.1109/LSP.2023.3283541
10.1109/TCSVT.2020.2980571
10.1145/3581783.3612500
10.1109/TBC.2022.3165473
10.1109/CVPR.2019.00950
10.1109/CVPRW53098.2021.00030
10.1117/1.JEI.23.1.013016
10.1145/3343031.3351028
10.1109/TMM.2019.2895280
10.1109/TCSVT.2021.3088505
10.1016/j.cviu.2007.09.014
10.1109/TMM.2018.2817070
10.1109/TIP.2017.2662206
10.1109/CVPR52688.2022.00588
10.1109/TIP.2019.2923051
10.1109/TPAMI.2019.2944806
10.1145/3474085.3475710
10.1109/CVPRW56347.2022.00129
10.1109/ICME.2017.8019333
10.1007/s11042-020-09907-1
10.1109/CVPR.2019.01031
10.1109/CVPR.2018.00652
10.1007/978-3-030-27202-9_14
10.1117/12.2043128
10.1109/TIP.2003.819861
10.1109/ISCAS48785.2022.9937741
10.1109/TIP.2010.2042111
10.1145/3474085.3475477
10.1609/aaai.v37i3.25458
10.1109/TCSVT.2012.2221191
10.1609/aaai.v34i07.6697
10.1109/TCSVT.2024.3369073
10.1109/CVPR52688.2022.00578
10.1007/978-3-030-58517-4_17
10.1109/TIP.2018.2815841
10.1109/TMM.2023.3338087
10.1109/PCS48520.2019.8954503
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TMM.2024.3414549
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore Digital Library
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1941-0077
EndPage 10827
ExternalDocumentID 10_1109_TMM_2024_3414549
10584328
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62171134
  funderid: 10.13039/501100001809
– fundername: Natural Science Foundation and Technology Innovation Joint Fund Project of Fujian Province
  grantid: 2023J01395; 2023Y9346
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
TN5
VH1
ZY4
AAYXX
CITATION
ID FETCH-LOGICAL-c264t-67e1ccc7231350e8d0b5f01f51fcc7f480974b259c56fe1b47d2be73491229ed3
IEDL.DBID RIE
ISSN 1520-9210
IngestDate Tue Jul 01 01:54:44 EDT 2025
Thu Apr 24 23:09:53 EDT 2025
Wed Aug 27 03:04:56 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c264t-67e1ccc7231350e8d0b5f01f51fcc7f480974b259c56fe1b47d2be73491229ed3
ORCID 0000-0002-5900-4175
0009-0003-3748-3763
0000-0002-7497-8883
0000-0002-9789-6151
PageCount 12
ParticipantIDs ieee_primary_10584328
crossref_citationtrail_10_1109_TMM_2024_3414549
crossref_primary_10_1109_TMM_2024_3414549
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 20240000
2024-00-00
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 20240000
PublicationDecade 2020
PublicationTitle IEEE transactions on multimedia
PublicationTitleAbbrev TMM
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref57
ref12
ref56
ref15
ref59
ref14
ref58
ref53
ref52
ref11
ref55
ref54
ref17
ref16
ref19
ref18
ref51
ref46
ref45
ref47
ref42
ref44
ref43
(ref49) 1999
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Jianyu (ref40) 2019
ref35
Blu (ref36) 2018
ref37
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
(ref50) 2012
Moorthy (ref34) 2012
Shiqi (ref41) 2019
Bossen (ref48) 2013
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref29
Chen (ref27) 2022
Liu (ref10) 2023
References_xml – ident: ref47
  doi: 10.1109/TCSVT.2022.3227039
– ident: ref9
  doi: 10.1109/WACV48630.2021.00164
– start-page: 68420
  volume-title: Proc. 37th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track
  year: 2023
  ident: ref10
  article-title: Bitstream-corrupted video recovery: A novel benchmark dataset and method
– ident: ref28
  doi: 10.1007/s11760-019-01543-z
– ident: ref30
  doi: 10.3390/s21196429
– ident: ref55
  doi: 10.1109/ACSSC.2003.1292216
– year: 1999
  ident: ref49
  article-title: Methodology for the subjective assessment of video quality in multimedia applications
– ident: ref24
  doi: 10.1109/ICCV.2015.73
– ident: ref3
  doi: 10.1109/VCIP49819.2020.9301847
– ident: ref17
  doi: 10.1109/TBC.2022.3208426
– ident: ref19
  doi: 10.1109/TMM.2022.3214775
– ident: ref53
  doi: 10.1109/ICPR.2010.579
– ident: ref57
  doi: 10.1109/TIP.2015.2502725
– ident: ref46
  doi: 10.1109/TIP.2018.2889276
– ident: ref32
  doi: 10.1109/LSP.2023.3283541
– ident: ref5
  doi: 10.1109/TCSVT.2020.2980571
– ident: ref44
  doi: 10.1145/3581783.3612500
– ident: ref31
  doi: 10.1109/TBC.2022.3165473
– ident: ref52
  doi: 10.1109/CVPR.2019.00950
– ident: ref13
  doi: 10.1109/CVPRW53098.2021.00030
– ident: ref35
  doi: 10.1117/1.JEI.23.1.013016
– ident: ref58
  doi: 10.1145/3343031.3351028
– ident: ref20
  doi: 10.1109/TMM.2019.2895280
– start-page: 1
  volume-title: Proc. Joint Collaborative Team Video Coding Meeting
  year: 2013
  ident: ref48
  article-title: HM 10 common test conditions and software reference configurations
– ident: ref59
  doi: 10.1109/TCSVT.2021.3088505
– year: 2012
  ident: ref50
  article-title: Methodology for the subjective assessment of the quality of television pictures
– ident: ref51
  doi: 10.1016/j.cviu.2007.09.014
– year: 2018
  ident: ref36
  article-title: IVP video quality database
– start-page: 652
  volume-title: Proc. IEEE ICC Workshop Realizing Adv. Video Optimized Wireless Netw.
  year: 2012
  ident: ref34
  article-title: Mobile video quality assessment database
– ident: ref38
  doi: 10.1109/TMM.2018.2817070
– ident: ref25
  doi: 10.1109/TIP.2017.2662206
– ident: ref21
  doi: 10.1109/CVPR52688.2022.00588
– ident: ref29
  doi: 10.1109/TIP.2019.2923051
– ident: ref14
  doi: 10.1109/TPAMI.2019.2944806
– ident: ref16
  doi: 10.1145/3474085.3475710
– ident: ref23
  doi: 10.1109/CVPRW56347.2022.00129
– ident: ref56
  doi: 10.1109/ICME.2017.8019333
– ident: ref11
  doi: 10.1007/s11042-020-09907-1
– ident: ref1
  doi: 10.1109/CVPR.2019.01031
– ident: ref42
  doi: 10.1109/CVPR.2018.00652
– start-page: 1
  volume-title: Proc. 11th Int. Conf. Wireless Commun. Signal Process.
  year: 2019
  ident: ref41
  article-title: HEVC compression artifact reduction with generative adversarial networks
– start-page: 25478
  volume-title: Proc. Annu. Conf. Neural Inf. Process. Syst.
  year: 2022
  ident: ref27
  article-title: Cross aggregation transformer for image restoration
– ident: ref37
  doi: 10.1007/978-3-030-27202-9_14
– ident: ref45
  doi: 10.1117/12.2043128
– ident: ref54
  doi: 10.1109/TIP.2003.819861
– ident: ref15
  doi: 10.1109/ISCAS48785.2022.9937741
– ident: ref33
  doi: 10.1109/TIP.2010.2042111
– ident: ref7
  doi: 10.1145/3474085.3475477
– start-page: 1174
  volume-title: Proc. IEEE Int. Conf. Multimedia Expo
  year: 2019
  ident: ref40
  article-title: A video post-filter deblocking method based on temporal boosting residual networks
– ident: ref22
  doi: 10.1609/aaai.v37i3.25458
– ident: ref2
  doi: 10.1109/TCSVT.2012.2221191
– ident: ref12
  doi: 10.1609/aaai.v34i07.6697
– ident: ref43
  doi: 10.1109/TCSVT.2024.3369073
– ident: ref8
  doi: 10.1109/CVPR52688.2022.00578
– ident: ref6
  doi: 10.1109/CVPR52688.2022.00578
– ident: ref26
  doi: 10.1007/978-3-030-58517-4_17
– ident: ref39
  doi: 10.1109/TIP.2018.2815841
– ident: ref18
  doi: 10.1109/TMM.2023.3338087
– ident: ref4
  doi: 10.1109/PCS48520.2019.8954503
SSID ssj0014507
Score 2.4182184
Snippet Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art...
SourceID crossref
ieee
SourceType Enrichment Source
Index Database
Publisher
StartPage 10816
SubjectTerms Distortion
Encoding
Image coding
Perceivable encoding artifact
Quality assessment
Video compression
video compression artifact removal
video quality assessment
Title Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset
URI https://ieeexplore.ieee.org/document/10584328
Volume 26
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NT8IwFG-Ekx5EESN-pQcvHjb20W3UGwqEmMDBAOG2bO1rNMhmyLj41_vaDbOYaLwtTds1eW1_79f3Rchd4gMq_RBZYeKHFlORY3HpupYKFcJNHwFY6KeB6SycLNjzKlhVweomFgYAjPMZ2PrT2PJlLnb6qQxPOMKl7_UbpIHMrQzW-jYZsMDERiMe4e-QyOxtkg7vzadTZIIes_HKZoFOm1nDoFpRFYMp4xaZ7VdTupKs7V2R2uLzR6LGfy_3hBxX2iUdlNvhlBxA1iatfeUGWh3kNjmqpSE8I8u58Z2lI5NOAuekyzcJOdXjSjfZzEypgyDoEArjvZXRJJP0BTY57tUHOqCPOPXrJtmu6TApEBuLDlmMR_OniVXVW7AEqkWFFUbgCiEiVPn8wIG-dNJAOa4KXIWtivUdJB8p8iURhArclEXSSyHyGXc9j4P0z0kzyzO4INQXDk8VR7LEE-YmPJEp3vAeC6UUXKqwS3p7CcSiSkaua2K8x4aUODxGmcVaZnElsy65_x7xUSbi-KNvR0uj1q8UxOUv7VfkUA8vX1auSbPY7uAGdY0ivTV77Asecs7w
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED7xGICBN-KNBxaGlDhxkpqNR6vyaAdUEFuU2GeBSlNUpQu_nrOTogoJxBZZ9sXSnf3d-V4Ap1mIpPRj4sVZGHvCJL4nNeeeiQ3BTZMAWNmngW4v7jyJu5fopU5Wd7kwiOiCz7BhP50vX4_UxD6V0QknuAyD5jwsEvBHvErX-nYaiMhlRxMi0Q_JlJl6JX153u92yRYMRIMubRHZwpkzKDTTVsWhSnsNetP9VMEkg8akzBvq80epxn9veB1Wa_2SXVYCsQFzWGzC2rR3A6uP8iaszBQi3ILnvoueZS1XUIJosuc3jSNm11WBsoUjadMg2A2WLn6rYFmh2SMORyStF-ySXRHp12E2HrCbrCR0LLfhqd3qX3e8uuOCp0gxKr04Qa6USkjpCyMfm9rPI-NzE3FDo0Y0fTI_crKYVBQb5LlIdJBjEgrJg0CiDndgoRgVuAssVL7MjSRzSWaCZzLTOd3xgYi1VlKbeA_OpxxIVV2O3HbFeE-dWeLLlHiWWp6lNc_24Ox7xUdViuOPuduWGzPzKkbs_zJ-Akudfvchfbjt3R_AsiVVvbMcwkI5nuARaR5lfuzk7QsWPdI5
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=Toward+Efficient+Video+Compression+Artifact+Detection+and+Removal%3A+A+Benchmark+Dataset&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Lin%2C+Liqun&rft.au=Wang%2C+Mingxing&rft.au=Yang%2C+Jing&rft.au=Zhang%2C+Keke&rft.date=2024&rft.issn=1520-9210&rft.eissn=1941-0077&rft.volume=26&rft.spage=10816&rft.epage=10827&rft_id=info:doi/10.1109%2FTMM.2024.3414549&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2024_3414549
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon