Blur Removal Via Blurred-Noisy Image Pair

Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acqui...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on image processing Ročník 30; s. 345 - 359
Hlavní autoři: Gu, Chunzhi, Lu, Xuequan, He, Ying, Zhang, Chao
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1057-7149, 1941-0042, 1941-0042
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acquired in low-light situations: (1) a blurred image taken with low shutter speed and low ISO noise; and (2) a noisy image captured with high shutter speed and high ISO noise. Slicing the blurred image into patches, we extend the Gaussian mixture model (GMM) to model the underlying intensity distribution of each patch using the corresponding patches in the noisy image. We compute patch correspondences by analyzing the optical flow between the two images. The Expectation Maximization (EM) algorithm is utilized to estimate the parameters of GMM. To preserve sharp features, we add an additional bilateral term to the objective function in the M-step. We eventually add a detail layer to the deblurred image for refinement. Extensive experiments on both synthetic and real-world data demonstrate that our method outperforms state-of-the-art techniques, in terms of robustness, visual quality, and quantitative metrics.
AbstractList Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acquired in low-light situations: (1) a blurred image taken with low shutter speed and low ISO noise; and (2) a noisy image captured with high shutter speed and high ISO noise. Slicing the blurred image into patches, we extend the Gaussian mixture model (GMM) to model the underlying intensity distribution of each patch using the corresponding patches in the noisy image. We compute patch correspondences by analyzing the optical flow between the two images. The Expectation Maximization (EM) algorithm is utilized to estimate the parameters of GMM. To preserve sharp features, we add an additional bilateral term to the objective function in the M-step. We eventually add a detail layer to the deblurred image for refinement. Extensive experiments on both synthetic and real-world data demonstrate that our method outperforms state-of-the-art techniques, in terms of robustness, visual quality, and quantitative metrics.
Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acquired in low-light situations: (1) a blurred image taken with low shutter speed and low ISO noise; and (2) a noisy image captured with high shutter speed and high ISO noise. Slicing the blurred image into patches, we extend the Gaussian mixture model (GMM) to model the underlying intensity distribution of each patch using the corresponding patches in the noisy image. We compute patch correspondences by analyzing the optical flow between the two images. The Expectation Maximization (EM) algorithm is utilized to estimate the parameters of GMM. To preserve sharp features, we add an additional bilateral term to the objective function in the M-step. We eventually add a detail layer to the deblurred image for refinement. Extensive experiments on both synthetic and real-world data demonstrate that our method outperforms state-of-the-art techniques, in terms of robustness, visual quality, and quantitative metrics.Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article, we propose a novel image deblurring method that does not need to estimate blur kernels. We utilize a pair of images that can be easily acquired in low-light situations: (1) a blurred image taken with low shutter speed and low ISO noise; and (2) a noisy image captured with high shutter speed and high ISO noise. Slicing the blurred image into patches, we extend the Gaussian mixture model (GMM) to model the underlying intensity distribution of each patch using the corresponding patches in the noisy image. We compute patch correspondences by analyzing the optical flow between the two images. The Expectation Maximization (EM) algorithm is utilized to estimate the parameters of GMM. To preserve sharp features, we add an additional bilateral term to the objective function in the M-step. We eventually add a detail layer to the deblurred image for refinement. Extensive experiments on both synthetic and real-world data demonstrate that our method outperforms state-of-the-art techniques, in terms of robustness, visual quality, and quantitative metrics.
Author Lu, Xuequan
Zhang, Chao
He, Ying
Gu, Chunzhi
Author_xml – sequence: 1
  givenname: Chunzhi
  orcidid: 0000-0001-7280-337X
  surname: Gu
  fullname: Gu, Chunzhi
  email: gu-cz@monju.fuis.u-fukui.ac.jp
  organization: School of Engineering, University of Fukui, Fukui, Japan
– sequence: 2
  givenname: Xuequan
  orcidid: 0000-0003-0959-408X
  surname: Lu
  fullname: Lu, Xuequan
  email: xuequan.lu@deakin.edu.au
  organization: School of Information Technology, Deakin University, Geelong, VIC, Australia
– sequence: 3
  givenname: Ying
  orcidid: 0000-0002-6749-4485
  surname: He
  fullname: He, Ying
  email: yhe@ntu.edu.sg
  organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore
– sequence: 4
  givenname: Chao
  orcidid: 0000-0002-0845-9217
  surname: Zhang
  fullname: Zhang, Chao
  email: zhang@u-fukui.ac.jp
  organization: School of Engineering, University of Fukui, Fukui, Japan
BookMark eNp9kMtLw0AQxhep2IfeBS8BL3pInX03Ry0-CkWLVK9hs5nIljSpu4nQ_96UFg89CAMzDL_vm-Ebkl5VV0jIJYUxpZDcLWeLMQMGYw5caSFPyIAmgsYAgvW6GaSONRVJnwxDWAFQIak6I33O6UR1BgNy-1C2PnrHdf1jyujTmWi38JjHr7UL22i2Nl8YLYzz5-S0MGXAi0MfkY-nx-X0JZ6_Pc-m9_PYciaaOAeWcctsriwrEjsxhhWMUiV1Vqgko3mRYZ7bbKJRK4R8AhkVItcSwUhukI_Izd534-vvFkOTrl2wWJamwroNKRMKtOIaVIdeH6GruvVV992OkkLwJJEdBXvK-joEj0W68W5t_DalkO5iTLsY012M6SHGTqKOJNY1pnF11Xjjyv-EV3uhQ8S_OwmTXTH-C4zQfUs
CODEN IIPRE4
CitedBy_id crossref_primary_10_1007_s00371_024_03632_8
crossref_primary_10_1016_j_icte_2025_06_003
crossref_primary_10_1016_j_patcog_2022_108716
crossref_primary_10_1109_JIOT_2023_3268285
crossref_primary_10_3390_s24196425
crossref_primary_10_1111_mice_70001
crossref_primary_10_1109_TNNLS_2023_3329712
crossref_primary_10_1051_smdo_2025008
crossref_primary_10_1134_S1054661822030270
crossref_primary_10_1007_s11263_022_01633_5
crossref_primary_10_1109_TCSVT_2021_3135337
crossref_primary_10_3390_s23083784
Cites_doi 10.1109/ICCV.2011.6126544
10.1111/j.1467-8659.2012.03211.x
10.1109/CVPR.2017.35
10.1109/TIP.2020.3015545
10.1109/CVPR.2014.430
10.1007/978-1-4757-5348-6_24
10.1109/CVPR.2005.38
10.1109/CVPR.2017.738
10.1109/ICCV.2015.36
10.1145/1618452.1618491
10.1109/CVPR.2015.7298852
10.1007/s11263-011-0502-7
10.1109/CVPR.2010.5539941
10.1109/CVPR.2010.5540158
10.1109/CVPR.2014.374
10.1007/BF01420984
10.1109/ICCV.2015.76
10.1007/3-540-45103-X_50
10.1109/TIP.2020.2972109
10.1007/3-540-57956-7_5
10.1109/TIP.2014.2362059
10.1109/ICCV.2017.486
10.1109/CVPR.2019.00181
10.1109/CVPR.2018.00345
10.1007/s11263-010-0390-2
10.1109/CVPR.2014.432
10.1109/ICIP.2016.7533014
10.1109/TIP.2015.2442914
10.1109/CVPR.2009.5206815
10.1117/12.766355
10.1109/ICCV.2011.6126278
10.1109/TCOM.1983.1095851
10.1016/j.cviu.2019.102792
10.1109/CVPR.2013.147
10.1145/1141911.1141956
10.1109/CVPR.2010.5540171
10.1109/TIP.2017.2753658
10.1109/TIP.2016.2590318
10.1109/TVCG.2017.2725948
10.1016/j.jcp.2009.04.022
10.1109/MLSP.2016.7738841
10.1109/TIP.2020.3005515
10.1111/j.2517-6161.1977.tb01600.x
10.1109/ICIP.2017.8296824
10.1109/CVPR.2013.140
10.1109/CVPR.2011.5995521
10.5120/20396-2697
10.1364/DIPA.2010.DMC1
10.1109/TIP.2014.2323127
10.1109/ICIP.2016.7532658
10.1145/1360612.1360672
10.1145/1276377.1276379
10.1364/JOSA.62.000055
10.1109/ICCV.1998.710815
10.1109/CVPR.2008.4587834
10.1007/978-3-642-33715-4_46
10.1109/TIP.2018.2874290
10.1109/CVPR.2011.5995351
10.1007/978-3-642-15549-9_12
10.1109/TIP.2011.2108306
10.1109/ICCCI.2016.7479956
10.1109/TIP.2011.2175740
10.1109/TPAMI.2010.46
10.1109/CVPR.2018.00854
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TIP.2020.3036745
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
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
MEDLINE - Academic
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
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
EISSN 1941-0042
EndPage 359
ExternalDocumentID 10_1109_TIP_2020_3036745
9259252
Genre orig-research
GrantInformation_xml – fundername: Grant CY01-251301-F003-PJ03906-PG00447 and Grant PJ06625
– fundername: Japan Society for the Promotion of Science (JSPS) KAKENHI (Grant-in-Aid for Scientific Research)
  grantid: JP20K19568
  funderid: 10.13039/501100001691
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c324t-d02b3c2cd6c2f9c8aa2f211657bf69b1dfbeddcb87e76e0d80b144d75e0a53ae3
IEDL.DBID RIE
ISICitedReferencesCount 19
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000595466700005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1057-7149
1941-0042
IngestDate Sun Sep 28 09:20:04 EDT 2025
Mon Jun 30 10:14:22 EDT 2025
Tue Nov 18 22:32:50 EST 2025
Sat Nov 29 03:21:13 EST 2025
Wed Aug 27 02:27:30 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-c324t-d02b3c2cd6c2f9c8aa2f211657bf69b1dfbeddcb87e76e0d80b144d75e0a53ae3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-0845-9217
0000-0002-6749-4485
0000-0003-0959-408X
0000-0001-7280-337X
PMID 33186109
PQID 2465443995
PQPubID 85429
PageCount 15
ParticipantIDs ieee_primary_9259252
crossref_primary_10_1109_TIP_2020_3036745
crossref_citationtrail_10_1109_TIP_2020_3036745
proquest_miscellaneous_2460763706
proquest_journals_2465443995
PublicationCentury 2000
PublicationDate 20210000
2021-00-00
20210101
PublicationDateYYYYMMDD 2021-01-01
PublicationDate_xml – year: 2021
  text: 20210000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on image processing
PublicationTitleAbbrev TIP
PublicationYear 2021
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 ref57
ref13
ref56
ref12
ref59
ref15
ref58
ref14
ref53
ref52
ref55
ref54
ref10
artin (ref1) 2016
bishop (ref6) 1995
wang (ref51) 2014
ref17
ref16
ref19
ref18
ref50
lu (ref34) 2018; 24
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref4
ref3
zoran (ref70) 2012
ref5
ref40
ref35
ref37
ref36
ref31
ref30
ref33
ref2
ref39
ref38
ref68
ref24
ref67
ref23
ref26
ref69
ref25
ref64
ref20
ref63
ref66
ref22
ref65
ref21
ref28
ref27
ref29
lu (ref32) 2018
ref60
ref62
ref61
chen (ref11) 2008
References_xml – ident: ref41
  doi: 10.1109/ICCV.2011.6126544
– ident: ref12
  doi: 10.1111/j.1467-8659.2012.03211.x
– ident: ref38
  doi: 10.1109/CVPR.2017.35
– ident: ref61
  doi: 10.1109/TIP.2020.3015545
– ident: ref22
  doi: 10.1109/CVPR.2014.430
– ident: ref24
  doi: 10.1007/978-1-4757-5348-6_24
– ident: ref7
  doi: 10.1109/CVPR.2005.38
– ident: ref57
  doi: 10.1109/CVPR.2017.738
– ident: ref53
  doi: 10.1109/ICCV.2015.36
– ident: ref13
  doi: 10.1145/1618452.1618491
– ident: ref15
  doi: 10.1109/CVPR.2015.7298852
– ident: ref52
  doi: 10.1007/s11263-011-0502-7
– ident: ref68
  doi: 10.1109/CVPR.2010.5539941
– ident: ref23
  doi: 10.1109/CVPR.2010.5540158
– ident: ref63
  doi: 10.1109/CVPR.2014.374
– ident: ref5
  doi: 10.1007/BF01420984
– start-page: 7226
  year: 2018
  ident: ref32
  article-title: Unsupervised articulated skeleton extraction from point set sequences captured by a single depth camera
  publication-title: Proc AAAI
– ident: ref10
  doi: 10.1109/ICCV.2015.76
– ident: ref19
  doi: 10.1007/3-540-45103-X_50
– ident: ref60
  doi: 10.1109/TIP.2020.2972109
– ident: ref39
  doi: 10.1007/3-540-57956-7_5
– ident: ref27
  doi: 10.1109/TIP.2014.2362059
– ident: ref45
  doi: 10.1109/ICCV.2017.486
– ident: ref21
  doi: 10.1109/CVPR.2019.00181
– ident: ref50
  doi: 10.1109/CVPR.2018.00345
– ident: ref4
  doi: 10.1007/s11263-010-0390-2
– ident: ref25
  doi: 10.1109/CVPR.2014.432
– ident: ref46
  doi: 10.1109/ICIP.2016.7533014
– ident: ref16
  doi: 10.1109/TIP.2015.2442914
– ident: ref30
  doi: 10.1109/CVPR.2009.5206815
– ident: ref14
  doi: 10.1117/12.766355
– ident: ref69
  doi: 10.1109/ICCV.2011.6126278
– ident: ref8
  doi: 10.1109/TCOM.1983.1095851
– ident: ref33
  doi: 10.1016/j.cviu.2019.102792
– ident: ref55
  doi: 10.1109/CVPR.2013.147
– ident: ref20
  doi: 10.1145/1141911.1141956
– ident: ref66
  doi: 10.1109/CVPR.2010.5540171
– ident: ref56
  doi: 10.1109/TIP.2017.2753658
– start-page: 1736
  year: 2012
  ident: ref70
  article-title: Natural images, Gaussian mixtures and dead leaves
  publication-title: Proc Adv Neural Inf Process Syst (NIPS)
– ident: ref35
  doi: 10.1109/TIP.2016.2590318
– volume: 24
  start-page: 2315
  year: 2018
  ident: ref34
  article-title: GPF: GMM-inspired feature-preserving point set filtering
  publication-title: IEEE Trans Vis Comput Graphics
  doi: 10.1109/TVCG.2017.2725948
– ident: ref9
  doi: 10.1016/j.jcp.2009.04.022
– ident: ref47
  doi: 10.1109/MLSP.2016.7738841
– ident: ref59
  doi: 10.1109/TIP.2020.3005515
– ident: ref17
  doi: 10.1111/j.2517-6161.1977.tb01600.x
– year: 2014
  ident: ref51
  article-title: Recent progress in image deblurring
  publication-title: arXiv 1409 6838
– ident: ref62
  doi: 10.1109/ICIP.2017.8296824
– ident: ref64
  doi: 10.1109/CVPR.2013.140
– year: 2016
  ident: ref1
  publication-title: Geometric Algebra
– year: 1995
  ident: ref6
  publication-title: Neural Networks for Pattern Recognition
– ident: ref28
  doi: 10.1109/CVPR.2011.5995521
– ident: ref49
  doi: 10.5120/20396-2697
– ident: ref44
  doi: 10.1364/DIPA.2010.DMC1
– ident: ref65
  doi: 10.1109/TIP.2014.2323127
– ident: ref2
  doi: 10.1109/ICIP.2016.7532658
– ident: ref42
  doi: 10.1145/1360612.1360672
– ident: ref58
  doi: 10.1145/1276377.1276379
– ident: ref40
  doi: 10.1364/JOSA.62.000055
– ident: ref48
  doi: 10.1109/ICCV.1998.710815
– start-page: 1
  year: 2008
  ident: ref11
  article-title: Robust dual motion deblurring
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref26
  doi: 10.1109/CVPR.2008.4587834
– ident: ref67
  doi: 10.1007/978-3-642-33715-4_46
– ident: ref3
  doi: 10.1109/TIP.2018.2874290
– ident: ref31
  doi: 10.1109/CVPR.2011.5995351
– ident: ref54
  doi: 10.1007/978-3-642-15549-9_12
– ident: ref18
  doi: 10.1109/TIP.2011.2108306
– ident: ref36
  doi: 10.1109/ICCCI.2016.7479956
– ident: ref43
  doi: 10.1109/TIP.2011.2175740
– ident: ref37
  doi: 10.1109/TPAMI.2010.46
– ident: ref29
  doi: 10.1109/CVPR.2018.00854
SSID ssj0014516
Score 2.5170722
Snippet Complex blur such as the mixup of space-variant and space-invariant blur, which is hard to model mathematically, widely exists in real images. In this article,...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 345
SubjectTerms Algorithms
Cameras
Estimation
Gaussian mixture model
Image acquisition
Image deblurring
Image restoration
Kernel
Noise measurement
optical flow
Optical flow (image analysis)
Optical imaging
Parameter estimation
Probabilistic models
Robustness (mathematics)
Slicing
Title Blur Removal Via Blurred-Noisy Image Pair
URI https://ieeexplore.ieee.org/document/9259252
https://www.proquest.com/docview/2465443995
https://www.proquest.com/docview/2460763706
Volume 30
WOSCitedRecordID wos000595466700005&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0042
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014516
  issn: 1057-7149
  databaseCode: RIE
  dateStart: 19920101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LaxsxEB5ck0N6iPNoifNiA70EsrWslfU4tiEhvhhTkuDboicYEm9Y24X--4zk9RJIKfS27I4WMRqN5qVvAL5RwlXQVObBFiJH_ysGmqzPA-eMFBErMITUbEJMJnI2U9MOXLd3Ybz3qfjMf4-PKZfvKruOobKBQludjlDhfhKCb-5qtRmD2HA2ZTZHIhdo9m9TkkQNHsZTdAQp-qeorgWLzWpwFpKnKsR3p1Fqr_JBJ6eD5q73f1Pch73GoMx-bCTgADp-cQi9xrjMmq27PITP75AHj-Dq5_O6zn75lwolLXua6yy-qL3LJ9V8-Scbv6CeyaZ6Xn-Bx7vbh5v7vOmakFs0jla5I9QUllrHLQ3KSq1poBFkR5jAlRm6YLxz1kjhBffESWLQqXJi5IkeFdoXX6G7qBb-GDIzpDZiRQ2tYowZqYixBWOUOcO0LEgfBlvulbaBFI-dLZ7L5FoQVSLry8j6smF9H67aEa8bOI1_0B5F_rZ0DWv7cLZdoLLZb8uSRli46FrhqMv2M-6UmP7QC1-tEw1BbSoIP_n7n09hl8aKlRRgOYPuql77c9ixv1fzZX2BQjeTF0no3gAVds5h
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS-wwEB5EhaMP3sX1WuG8CKduNk2b5lFFcVGXRfYcfCu5woJupbsr-O-dZLtFOCL4VtqkhC-TyUxm8g3Ab0oy4STNY6cTHqP_5Q-atI1dljGSeK5A50KxCd7r5U9Por8Af5q7MNbakHxmz_1jiOWbUk_9UVlboK1OU1S4SyljlMxuazUxA19yNsQ2Ux5zNPznQUki2oNuH11Bih4qKmzOfLkaHEeehTzET_tRKLDyn1YOW83N-s8GuQFrtUkZXcxkYBMW7GgL1mvzMqoX73gLVj9xD27D2eXztIoe7UuJshb9G8rIv6isiXvlcPwedV9Q00R9Oax24O_N9eDqNq7rJsQazaNJbAhViabaZJo6oXMpqaOeZocrlwnVMU5ZY7TKueWZJSYnCt0qw1NLZJpIm-zC4qgc2T2IVIdqzxbV0YIxpnJBlE4Qe2YUk3lCWtCeo1fomlTc17Z4LoJzQUSB0Bce-qKGvgVnTY_XGaHGN223Pb5NuxraFhzOJ6ioV9y4oJ4YzjtX2Ou0-YxrxQdA5MiW09CGoD7lJNv_-s8n8Ot28HBf3Hd7dwewQn3-SjhuOYTFSTW1R7Cs3ybDcXUcRO8DIMzQwA
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=Blur+Removal+Via+Blurred-Noisy+Image+Pair&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Gu%2C+Chunzhi&rft.au=Lu%2C+Xuequan&rft.au=He%2C+Ying&rft.au=Zhang%2C+Chao&rft.date=2021&rft.pub=IEEE&rft.issn=1057-7149&rft.volume=30&rft.spage=345&rft.epage=359&rft_id=info:doi/10.1109%2FTIP.2020.3036745&rft_id=info%3Apmid%2F33186109&rft.externalDocID=9259252
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon