Image-Scale-Symmetric Cooperative Network for Defocus Blur Detection

Defocus blur detection (DBD) for natural images is a challenging vision task especially in the presence of homogeneous regions and gradual boundaries. In this paper, we propose a novel image-scale-symmetric cooperative network (IS2CNet) for DBD. On one hand, in the process of image scales from large...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on circuits and systems for video technology Vol. 32; no. 5; pp. 2719 - 2731
Main Authors Zhao, Fan, Lu, Huimin, Zhao, Wenda, Yao, Libo
Format Journal Article
LanguageEnglish
Published New York IEEE 01.05.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Cooperative systems
Defocus blur detection
Feature extraction
Fuses
hierarchical feature integration
Image reconstruction
Image resolution
image-scale-symmetric cooperative networks
Ions
Semantics
Task analysis
Online AccessGet full text

Cover

Abstract Defocus blur detection (DBD) for natural images is a challenging vision task especially in the presence of homogeneous regions and gradual boundaries. In this paper, we propose a novel image-scale-symmetric cooperative network (IS2CNet) for DBD. On one hand, in the process of image scales from large to small, IS2CNet gradually spreads the recept of image content. Thus, the homogeneous region detection map can be optimized gradually. On the other hand, in the process of image scales from small to large, IS2CNet gradually feels the high-resolution image content, thereby gradually refining transition region detection. In addition, we propose a hierarchical feature integration and bi-directional delivering mechanism to transfer the hierarchical feature of previous image scale network to the input and tail of the current image scale network for guiding the current image scale network to better learn the residual. The proposed approach achieves state-of-the-art performance on existing datasets. Codes and results are available at: https://github.com/wdzhao123/IS2CNet .
AbstractList Defocus blur detection (DBD) for natural images is a challenging vision task especially in the presence of homogeneous regions and gradual boundaries. In this paper, we propose a novel image-scale-symmetric cooperative network (IS2CNet) for DBD. On one hand, in the process of image scales from large to small, IS2CNet gradually spreads the recept of image content. Thus, the homogeneous region detection map can be optimized gradually. On the other hand, in the process of image scales from small to large, IS2CNet gradually feels the high-resolution image content, thereby gradually refining transition region detection. In addition, we propose a hierarchical feature integration and bi-directional delivering mechanism to transfer the hierarchical feature of previous image scale network to the input and tail of the current image scale network for guiding the current image scale network to better learn the residual. The proposed approach achieves state-of-the-art performance on existing datasets. Codes and results are available at: https://github.com/wdzhao123/IS2CNet .
Author Zhao, Fan
Zhao, Wenda
Yao, Libo
Lu, Huimin
Author_xml – sequence: 1
  givenname: Fan
  orcidid: 0000-0003-2230-303X
  surname: Zhao
  fullname: Zhao, Fan
  email: fan_zhao20@163.com
  organization: School of Physics and Electronic Technology, Liaoning Normal University, Dalian, China
– sequence: 2
  givenname: Huimin
  surname: Lu
  fullname: Lu, Huimin
  email: bolandi@m.ieice.org
  organization: Kyushu Institute of Technology, Kitakyushu, Japan
– sequence: 3
  givenname: Wenda
  orcidid: 0000-0002-7463-6103
  surname: Zhao
  fullname: Zhao, Wenda
  email: zhaowenda@dlut.edu.cn
  organization: School of Information and Communication Engineering, Dalian University of Technology, Dalian, China
– sequence: 4
  givenname: Libo
  surname: Yao
  fullname: Yao, Libo
  email: ylb_rs@126.com
  organization: Research Institute of Information Fusion, Naval Aviation University, Yantai, China
BookMark eNo9kE1PwkAQhjcGEwH9A3pp4rk4sx_t7lHBDxKiB9Drpm6npki7uG01_HuLEC_zkbzPTPKM2KD2NTF2iTBBBHOzmi7fVhMOHCcCjBIyPWFDVErHnIMa9DMojDVHdcZGTbMGQKllOmSzeZV9ULx02aavu6qiNpQumnq_pZC15TdFz9T--PAZFT5EMyq865robtPtl5ZcW_r6nJ0W2aahi2Mfs9eH-9X0KV68PM6nt4vYSYQ2NgkColZSFBmZNOciMZBjKqTmuSNhFCV5ocFIAVmhCVxKGaJAjbyQ9C7G7Ppwdxv8V0dNa9e-C3X_0vJEGSGFNtin-CHlgm-aQIXdhrLKws4i2L0t-2fL7m3Zo60eujpAJRH9A0amCSCIXxBaZow
CODEN ITCTEM
CitedBy_id crossref_primary_10_1007_s11263_024_02058_y
crossref_primary_10_1016_j_imavis_2023_104845
crossref_primary_10_1109_TMM_2021_3134565
crossref_primary_10_1109_TIP_2023_3277793
crossref_primary_10_1016_j_cogr_2022_08_002
crossref_primary_10_1109_TIP_2023_3240856
crossref_primary_10_1063_5_0212675
crossref_primary_10_1007_s40747_023_01093_5
crossref_primary_10_1109_TMM_2023_3334023
crossref_primary_10_1109_TCI_2024_3354427
crossref_primary_10_1016_j_asoc_2022_109684
crossref_primary_10_1016_j_compeleceng_2022_108194
crossref_primary_10_1109_TMM_2023_3248162
crossref_primary_10_1587_transinf_2021EDP7181
crossref_primary_10_3390_s22072724
Cites_doi 10.1109/CVPR.2017.563
10.1111/cgf.13567
10.1109/TCSVT.2016.2602308
10.1109/CVPR.2018.00853
10.1109/ICCV.2017.179
10.1109/TPAMI.2019.2906588
10.1109/TPAMI.2015.2439281
10.1016/j.inffus.2021.06.002
10.1109/TMM.2020.2985541
10.1109/CVPR.2019.00281
10.1109/ICIP.2016.7533103
10.1109/CVPR.2009.5206596
10.1109/TCSVT.2018.2832086
10.1109/ICIP.2018.8451765
10.1109/ICCV.2017.574
10.1109/CVPR.2017.295
10.1109/CVPR.2016.90
10.1109/CVPR.2018.00179
10.1016/j.patcog.2020.107485
10.1109/TPAMI.2018.2846598
10.1109/CVPR.2019.01250
10.1109/CVPR.2014.379
10.1109/TMM.2020.3016123
10.1111/j.1467-8659.2007.01080.x
10.1109/TIP.2019.2893535
10.1109/TIP.2016.2528042
10.1109/ICCV.2019.00366
10.1109/TIP.2011.2162739
10.1364/OL.38.001706
10.1109/CVPR.2017.660
10.1007/978-3-030-58607-2_36
10.1109/CVPR.2019.00975
10.1016/j.neucom.2018.01.041
10.1109/ICCV.2017.487
10.1109/TIP.2021.3084101
10.1007/978-3-319-24574-4_28
10.1109/CVPR.2015.7298665
10.1109/TPAMI.2020.3014629
10.1109/TCSVT.2020.2990623
10.1109/TCSVT.2018.2821177
10.1007/978-3-030-01219-9_25
10.1109/TIP.2019.2908065
10.1109/CVPR.2019.00911
10.1109/TIP.2016.2555702
10.1109/TCSVT.2019.2944915
10.1109/TIP.2019.2942505
10.1109/CVPR.2019.00767
10.1109/LSP.2016.2611608
10.1109/CVPR.2016.396
10.1109/CVPR46437.2021.00686
10.1109/CVPR.2018.00325
10.1109/CVPR.2017.71
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TCSVT.2021.3095347
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2205
EndPage 2731
ExternalDocumentID 10_1109_TCSVT_2021_3095347
9476010
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62001450; 61801077
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AASAJ
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AI.
AIBXA
AKJIK
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RIG
RNS
RXW
TAE
TN5
VH1
XFK
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c410t-9610118543fae97d23690d173482dce395e6df809430af8e0c7ea1131812f4eb3
IEDL.DBID RIE
ISSN 1051-8215
IngestDate Fri Sep 13 08:14:27 EDT 2024
Fri Aug 23 00:10:20 EDT 2024
Wed Jun 26 19:31:20 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c410t-9610118543fae97d23690d173482dce395e6df809430af8e0c7ea1131812f4eb3
ORCID 0000-0003-2230-303X
0000-0002-7463-6103
PQID 2659343891
PQPubID 85433
PageCount 13
ParticipantIDs proquest_journals_2659343891
ieee_primary_9476010
crossref_primary_10_1109_TCSVT_2021_3095347
PublicationCentury 2000
PublicationDate 2022-05-01
PublicationDateYYYYMMDD 2022-05-01
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-05-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on circuits and systems for video technology
PublicationTitleAbbrev TCSVT
PublicationYear 2022
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
ref57
ref12
ref15
ref14
ref11
Simonyan (ref52)
ref55
ref10
ref54
ref17
ref16
ref19
ref18
Vaswani (ref56)
ref50
Kingma (ref53) 2014
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
Karaali (ref51) 2020
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
References_xml – ident: ref35
  doi: 10.1109/CVPR.2017.563
– ident: ref37
  doi: 10.1111/cgf.13567
– ident: ref27
  doi: 10.1109/TCSVT.2016.2602308
– ident: ref21
  doi: 10.1109/CVPR.2018.00853
– ident: ref7
  doi: 10.1109/ICCV.2017.179
– ident: ref38
  doi: 10.1109/TPAMI.2019.2906588
– ident: ref30
  doi: 10.1109/TPAMI.2015.2439281
– ident: ref33
  doi: 10.1016/j.inffus.2021.06.002
– ident: ref44
  doi: 10.1109/TMM.2020.2985541
– ident: ref14
  doi: 10.1109/CVPR.2019.00281
– ident: ref22
  doi: 10.1109/ICIP.2016.7533103
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Represent.
  ident: ref52
  article-title: Very deep convolutional networks for large-scale image recognition
  contributor:
    fullname: Simonyan
– ident: ref54
  doi: 10.1109/CVPR.2009.5206596
– ident: ref1
  doi: 10.1109/TCSVT.2018.2832086
– ident: ref13
  doi: 10.1109/ICIP.2018.8451765
– ident: ref6
  doi: 10.1109/ICCV.2017.574
– ident: ref10
  doi: 10.1109/CVPR.2017.295
– ident: ref18
  doi: 10.1109/CVPR.2016.90
– ident: ref31
  doi: 10.1109/CVPR.2018.00179
– ident: ref50
  doi: 10.1016/j.patcog.2020.107485
– ident: ref15
  doi: 10.1109/TPAMI.2018.2846598
– ident: ref49
  doi: 10.1109/CVPR.2019.01250
– year: 2014
  ident: ref53
  article-title: Adam: A method for stochastic optimization
  publication-title: arXiv:1412.6980
  contributor:
    fullname: Kingma
– ident: ref9
  doi: 10.1109/CVPR.2014.379
– ident: ref32
  doi: 10.1109/TMM.2020.3016123
– ident: ref43
  doi: 10.1109/CVPR.2019.00281
– ident: ref4
  doi: 10.1111/j.1467-8659.2007.01080.x
– ident: ref34
  doi: 10.1109/TIP.2019.2893535
– ident: ref8
  doi: 10.1109/TIP.2016.2528042
– ident: ref46
  doi: 10.1109/ICCV.2019.00366
– year: 2020
  ident: ref51
  article-title: Deep multi-scale feature learning for defocus blur estimation
  publication-title: arXiv:2009.11939
  contributor:
    fullname: Karaali
– ident: ref3
  doi: 10.1109/TIP.2011.2162739
– start-page: 5998
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref56
  article-title: Attention is all you need
  contributor:
    fullname: Vaswani
– ident: ref23
  doi: 10.1364/OL.38.001706
– ident: ref20
  doi: 10.1109/CVPR.2017.660
– ident: ref48
  doi: 10.1007/978-3-030-58607-2_36
– ident: ref47
  doi: 10.1109/CVPR.2019.00975
– ident: ref36
  doi: 10.1016/j.neucom.2018.01.041
– ident: ref55
  doi: 10.1109/ICCV.2017.487
– ident: ref40
  doi: 10.1109/TIP.2021.3084101
– ident: ref19
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref24
  doi: 10.1109/CVPR.2015.7298665
– ident: ref42
  doi: 10.1109/TPAMI.2020.3014629
– ident: ref29
  doi: 10.1109/TCSVT.2020.2990623
– ident: ref2
  doi: 10.1109/TCSVT.2018.2821177
– ident: ref16
  doi: 10.1007/978-3-030-01219-9_25
– ident: ref57
  doi: 10.1109/TIP.2019.2908065
– ident: ref39
  doi: 10.1109/CVPR.2019.00911
– ident: ref26
  doi: 10.1109/TIP.2016.2555702
– ident: ref28
  doi: 10.1109/TCSVT.2019.2944915
– ident: ref12
  doi: 10.1109/TIP.2019.2942505
– ident: ref45
  doi: 10.1109/CVPR.2019.00767
– ident: ref25
  doi: 10.1109/LSP.2016.2611608
– ident: ref17
  doi: 10.1109/CVPR.2016.396
– ident: ref41
  doi: 10.1109/CVPR46437.2021.00686
– ident: ref11
  doi: 10.1109/CVPR.2018.00325
– ident: ref5
  doi: 10.1109/CVPR.2017.71
SSID ssj0014847
Score 2.4984975
Snippet Defocus blur detection (DBD) for natural images is a challenging vision task especially in the presence of homogeneous regions and gradual boundaries. In this...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Publisher
StartPage 2719
SubjectTerms Cooperative systems
Defocus blur detection
Feature extraction
Fuses
hierarchical feature integration
Image reconstruction
Image resolution
image-scale-symmetric cooperative networks
Ions
Semantics
Task analysis
Title Image-Scale-Symmetric Cooperative Network for Defocus Blur Detection
URI https://ieeexplore.ieee.org/document/9476010
https://www.proquest.com/docview/2659343891/abstract/
Volume 32
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PT4MwFG7mTnrw1zROp-HgTWFAS6FH3VymyXbZZnYj0B8XHSwODvrX-1pgWdSDFwJJCc17pf2-9nvvIXRLBAkk9oCphkQBQVGpDbg5tWnEw5TqaM1Ubw1MpnS8IC_LYNlC99tYGCmlEZ9JR9-as3yR81JvlfUZ0QoOIOh7ketXsVrbEwMSmWJiABc8O4J1rAmQcVl_Ppi9zoEK-p6DdXo1XUplZxEyVVV-TcVmfRkdoUnTs0pW8uaURerwrx9JG__b9WN0WANN66EaGSeoJbNTdLCTfrCDhs8rmE3sGbgJrp-rla6uxa1Bnq9llRDcmlYqcQugrTWUCr6zsR7fS_1QGBFXdoYWo6f5YGzXVRVsTjy3sBkAJmAVAcEqkSwUPgaCLDyT5UZwiVkgqVCRVhy6iYqky0OZeB7WUEAR4N7nqJ3lmbxAliv81KeKYEETIhVnIkgY5thVQSp8irvorjFzvK6SZ8SGdLgsNk6JtVPi2ild1NF227asTdZFvcYzcf1_bWKfBgzrwu3e5d9vXaF9XwcqGGliD7WLj1JeA3wo0hszbr4BLia_xA
link.rule.ids 315,786,790,802,27957,27958,55109
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT8JAEJ0QPKgHv9CIovbgTQttd1u6RwUJKHABDLem3Y-LQomUg_56Z7eFEPXgpWmTbbrZ2e68t_tmBuCWCupL4iJTbVKFBEUlNuLmxA5C3kwCHa2Z6K2BwTDoTujz1J-W4H4TCyOlNOIzWde35ixfpHylt8oajGoFBxL0HfTzDsujtTZnBjQ05cQQMLh2iJ5sHSLjsMa4NXodIxn03DrRCdZ0MZUtN2TqqvxajI2H6RzCYN23XFjyVl9lSZ1__Ujb-N_OH8FBATWth3xuHENJzk9gfysBYQXavRmuJ_YIDYXXz9lM19fiVitNFzJPCW4Nc524heDWakuF31laj-8r_ZAZGdf8FCadp3Graxd1FWxOXSezGUIm5BU-JSqWrCk8ghRZuCbPjeCSMF8GQoVac-jEKpQOb8rYdYkGA4oi-z6D8jydy3OwHOElXqAoEUFMpeJM-DEjnDjKT4QXkCrcrYc5WuTpMyJDOxwWGaNE2ihRYZQqVPS4bVoWQ1aF2toyUfGHLSMv8BnRpdvdi7_fuoHd7njQj_q94csl7Hk6bMEIFWtQzj5W8grBRJZcmzn0DXyzwxo
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=Image-Scale-Symmetric+Cooperative+Network+for+Defocus+Blur+Detection&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Zhao%2C+Fan&rft.au=Lu%2C+Huimin&rft.au=Zhao%2C+Wenda&rft.au=Yao%2C+Libo&rft.date=2022-05-01&rft.pub=IEEE&rft.issn=1051-8215&rft.eissn=1558-2205&rft.volume=32&rft.issue=5&rft.spage=2719&rft.epage=2731&rft_id=info:doi/10.1109%2FTCSVT.2021.3095347&rft.externalDocID=9476010
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon