Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typicall...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of computer vision Ročník 133; číslo 10; s. 6953 - 6970
Hlavní autori: Ren, Dongwei, Shu, Xinya, Li, Yu, Wu, Xiaohe, Li, Jin, Zuo, Wangmeng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.10.2025
Springer Nature B.V
Predmet:
ISSN:0920-5691, 1573-1405
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research. The effectiveness of our method is validated by notable improvements in both quantitative metrics and visual quality across several datasets with real-world defocus blurry images, including DPDD, RealDOF, DED, and our SDD. The source code and dataset are available at  https://github.com/ssscrystal/Reblurring-guided-JDRL .
AbstractList For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research. The effectiveness of our method is validated by notable improvements in both quantitative metrics and visual quality across several datasets with real-world defocus blurry images, including DPDD, RealDOF, DED, and our SDD. The source code and dataset are available at  https://github.com/ssscrystal/Reblurring-guided-JDRL .
For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research. The effectiveness of our method is validated by notable improvements in both quantitative metrics and visual quality across several datasets with real-world defocus blurry images, including DPDD, RealDOF, DED, and our SDD. The source code and dataset are available at https://github.com/ssscrystal/Reblurring-guided-JDRL.
Author Ren, Dongwei
Li, Yu
Wu, Xiaohe
Zuo, Wangmeng
Shu, Xinya
Li, Jin
Author_xml – sequence: 1
  givenname: Dongwei
  orcidid: 0000-0002-0965-6810
  surname: Ren
  fullname: Ren, Dongwei
  email: rendongweihit@gmail.com
  organization: College of Intelligence and Computing, Tianjin University
– sequence: 2
  givenname: Xinya
  surname: Shu
  fullname: Shu, Xinya
  organization: Faculty of Computing, Harbin Institute of Technology
– sequence: 3
  givenname: Yu
  surname: Li
  fullname: Li, Yu
  organization: Faculty of Computing, Harbin Institute of Technology
– sequence: 4
  givenname: Xiaohe
  surname: Wu
  fullname: Wu, Xiaohe
  organization: Faculty of Computing, Harbin Institute of Technology
– sequence: 5
  givenname: Jin
  surname: Li
  fullname: Li, Jin
  organization: School of Electrical and Information Engineering, Tianjin University
– sequence: 6
  givenname: Wangmeng
  surname: Zuo
  fullname: Zuo, Wangmeng
  organization: Faculty of Computing, Harbin Institute of Technology
BookMark eNp9kEtPAjEUhRuDiYD-AVdNXFf7mM7DHUFBEoxGcd10OrdYHGawZUL89xbQuHNxc87inHOTb4B6TdsAQpeMXjNKs5vAGE8FoVzuj3MiTlCfyUwQllDZQ31acEpkWrAzNAhhRSnlORd9ZF-grDvvXbMk085VUOHX6GvAs7VeAr4D25ouRP2N3eIRnoP2TfR44vUadq3_wDu3fcePLujaLZu4svDaHSLP2vlwjk6trgNc_OgQvU3uF-MHMn-azsajOTE841tSAUsMyNyK0srUaEgNJJkGk5cMEqCVNRXnHHJWldxAmRSJpWCzxAiWClqIIbo67m58-9lB2KpV2_kmvlSCy6KQjAsZU_yYMr4NwYNVG-_W2n8pRtWepzryVJGlOvBUIpbEsRQ2ewzg_6b_aX0DDwh7eA
Cites_doi 10.1016/j.imavis.2024.105190
10.1609/aaai.v37i2.25235
10.1109/CVPR.2010.5540063
10.1109/CVPR52733.2024.00277
10.1109/CVPR.2018.00068
10.1109/CVPR52733.2024.01058
10.1109/CVPR52688.2022.00564
10.1145/3664647.3680888
10.1007/978-3-642-33715-4_45
10.1109/CVPR.2014.43
10.1109/CVPR52733.2024.00290
10.1109/CVPR.2017.295
10.1109/ICCPhot.2013.6528301
10.1109/ICIP49359.2023.10223146
10.1109/ICIP.1994.413553
10.1109/CVPRW.2019.00251
10.1109/TMM.2023.3334023
10.1109/ICCV48922.2021.00264
10.1109/ICCV.1998.710772
10.1109/CVPR52733.2024.02403
10.1109/CVPR52688.2022.01716
10.1109/CVPR.2018.00931
10.1109/CVPR42600.2020.00281
10.1109/TNNLS.2018.2876865
10.1109/CVPR.2018.00652
10.1007/978-3-030-58621-8_37
10.1109/TIP.2021.3127850
10.1364/JOSAA.12.000058
10.1109/CVPR52733.2024.02427
10.1109/CVPR52733.2024.02273
10.1007/978-3-642-15549-9_12
10.1109/CVPR52729.2023.01753
10.1109/CVPR52729.2023.00563
10.1109/ICCV48922.2021.00229
10.1109/CVPR52729.2023.00953
10.1007/978-3-030-58607-2_7
10.1109/CVPR.2015.7298665
10.1007/978-3-319-24574-4_28
10.1109/ICCV.2017.89
10.1109/CVPR52729.2023.00557
10.1109/CVPR46437.2021.01458
10.1109/CVPR.2015.7298642
10.1109/ICCV.2015.123
10.1109/JPROC.2023.3238524
10.1109/CVPR46437.2021.00207
10.1109/TIP.2003.819861
10.1109/ICCV51070.2023.01158
10.1109/CVPR.2019.00613
10.1109/ICCPHOT.2018.8368468
10.1109/CVPR52688.2022.00475
ContentType Journal Article
Copyright The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
Copyright_xml – notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
– notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1007/s11263-025-02522-3
DatabaseName CrossRef
Computer and Information Systems 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
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISSN 1573-1405
EndPage 6970
ExternalDocumentID 10_1007_s11263_025_02522_3
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62172127; U22B2035
  funderid: http://dx.doi.org/10.13039/501100001809
GroupedDBID -Y2
-~C
.4S
.86
.DC
.VR
06D
0R~
0VY
199
1N0
1SB
2.D
203
28-
29J
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
4.4
406
408
409
40D
40E
5GY
5QI
5VS
67Z
6NX
6TJ
78A
7WY
8FE
8FG
8FL
8TC
8UJ
95-
95.
95~
96X
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AAOBN
AAPKM
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBRH
ABBXA
ABDBE
ABDBF
ABDZT
ABECU
ABFSG
ABFTD
ABFTV
ABHLI
ABHQN
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABRTQ
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFO
ACGFS
ACHSB
ACHXU
ACIHN
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACREN
ACSTC
ACUHS
ACZOJ
ADHHG
ADHIR
ADHKG
ADIMF
ADKFA
ADKNI
ADKPE
ADMLS
ADRFC
ADTPH
ADURQ
ADYFF
ADYOE
ADZKW
AEAQA
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AEZWR
AFBBN
AFDZB
AFEXP
AFGCZ
AFHIU
AFKRA
AFLOW
AFOHR
AFQWF
AFWTZ
AFYQB
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGQPQ
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHPBZ
AHSBF
AHWEU
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AIXLP
AJBLW
AJRNO
AJZVZ
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMTXH
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
ATHPR
AVWKF
AXYYD
AYFIA
AYJHY
AZFZN
AZQEC
B-.
B0M
BA0
BBWZM
BDATZ
BENPR
BEZIV
BGLVJ
BGNMA
BPHCQ
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
DWQXO
EAD
EAP
EAS
EBLON
EBS
EDO
EIOEI
EJD
EMK
EPL
ESBYG
ESX
F5P
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNUQQ
GNWQR
GQ7
GQ8
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
I-F
I09
IAO
ICD
IHE
IJ-
IKXTQ
ISR
ITC
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Y
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K60
K6V
K6~
K7-
KDC
KOV
KOW
LAK
LLZTM
M0C
M4Y
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
OVD
P19
P2P
P62
P9O
PF0
PHGZM
PHGZT
PQBIZ
PQBZA
PQGLB
PQQKQ
PROAC
PT4
PT5
QF4
QM1
QN7
QO4
QOK
QOS
R4E
R89
R9I
RHV
RNI
RNS
ROL
RPX
RSV
RZC
RZE
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCJ
SCLPG
SCO
SDH
SDM
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TAE
TEORI
TSG
TSK
TSV
TUC
TUS
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WK8
YLTOR
Z45
ZMTXR
~8M
~EX
AAYXX
AFFHD
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c272t-de14ce58f3bf56cae6ce47aec8b1e4e0dfcd222e81db2ceb494f0ef74c3163093
IEDL.DBID RSV
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001524470700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0920-5691
IngestDate Wed Nov 05 09:05:05 EST 2025
Sat Nov 29 07:11:02 EST 2025
Sat Oct 11 06:45:36 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords Isotropic blur kernels
Reblurring model
Image deblurring
Defocus deblurring
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c272t-de14ce58f3bf56cae6ce47aec8b1e4e0dfcd222e81db2ceb494f0ef74c3163093
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0965-6810
PQID 3259951235
PQPubID 1456341
PageCount 18
ParticipantIDs proquest_journals_3259951235
crossref_primary_10_1007_s11263_025_02522_3
springer_journals_10_1007_s11263_025_02522_3
PublicationCentury 2000
PublicationDate 20251000
2025-10-00
20251001
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: 20251000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle International journal of computer vision
PublicationTitleAbbrev Int J Comput Vis
PublicationYear 2025
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References 2522_CR41
2522_CR42
2522_CR43
2522_CR44
2522_CR45
2522_CR46
2522_CR47
2522_CR48
2522_CR49
Yu Li (2522_CR20) 2023; 37
Zhong-Qiu Zhao (2522_CR53) 2019; 30
2522_CR30
2522_CR31
2522_CR32
2522_CR33
Xin Zhang (2522_CR51) 2024; 149
2522_CR34
2522_CR35
2522_CR36
2522_CR37
2522_CR38
2522_CR39
Haoyu Ma (2522_CR22) 2022; 31
2522_CR1
2522_CR2
2522_CR7
2522_CR8
2522_CR9
2522_CR21
2522_CR3
2522_CR23
2522_CR4
2522_CR24
2522_CR5
2522_CR25
2522_CR6
2522_CR26
2522_CR27
2522_CR28
2522_CR29
Zhengxia Zou (2522_CR54) 2023; 111
DA Fish (2522_CR11) 1995; 12
Zhou Wang (2522_CR40) 2004; 13
2522_CR50
2522_CR52
2522_CR10
2522_CR12
2522_CR13
2522_CR14
2522_CR15
2522_CR16
2522_CR17
2522_CR18
2522_CR19
References_xml – volume: 149
  year: 2024
  ident: 2522_CR51
  publication-title: Image and Vision Computing
  doi: 10.1016/j.imavis.2024.105190
– ident: 2522_CR30
– volume: 37
  start-page: 1495
  year: 2023
  ident: 2522_CR20
  publication-title: In Proceedings of the AAAI Conference on Artificial Intelligence
  doi: 10.1609/aaai.v37i2.25235
– ident: 2522_CR5
  doi: 10.1109/CVPR.2010.5540063
– ident: 2522_CR21
  doi: 10.1109/CVPR52733.2024.00277
– ident: 2522_CR48
  doi: 10.1109/CVPR.2018.00068
– ident: 2522_CR50
  doi: 10.1109/CVPR52733.2024.01058
– ident: 2522_CR46
  doi: 10.1109/CVPR52688.2022.00564
– ident: 2522_CR23
  doi: 10.1145/3664647.3680888
– ident: 2522_CR12
  doi: 10.1007/978-3-642-33715-4_45
– ident: 2522_CR19
  doi: 10.1109/CVPR.2014.43
– ident: 2522_CR25
– ident: 2522_CR26
  doi: 10.1109/CVPR52733.2024.00290
– ident: 2522_CR29
  doi: 10.1109/CVPR.2017.295
– ident: 2522_CR36
  doi: 10.1109/ICCPhot.2013.6528301
– ident: 2522_CR44
  doi: 10.1109/ICIP49359.2023.10223146
– ident: 2522_CR6
  doi: 10.1109/ICIP.1994.413553
– ident: 2522_CR24
  doi: 10.1109/CVPRW.2019.00251
– ident: 2522_CR52
  doi: 10.1109/TMM.2023.3334023
– ident: 2522_CR35
  doi: 10.1109/ICCV48922.2021.00264
– ident: 2522_CR27
  doi: 10.1109/ICCV.1998.710772
– ident: 2522_CR3
  doi: 10.1109/CVPR52733.2024.02403
– ident: 2522_CR39
  doi: 10.1109/CVPR52688.2022.01716
– ident: 2522_CR37
  doi: 10.1109/CVPR.2018.00931
– ident: 2522_CR49
  doi: 10.1109/CVPR42600.2020.00281
– volume: 30
  start-page: 3212
  issue: 11
  year: 2019
  ident: 2522_CR53
  publication-title: IEEE transactions on neural networks and learning systems
  doi: 10.1109/TNNLS.2018.2876865
– ident: 2522_CR4
  doi: 10.1109/CVPR.2018.00652
– ident: 2522_CR13
  doi: 10.1007/978-3-030-58621-8_37
– volume: 31
  start-page: 216
  year: 2022
  ident: 2522_CR22
  publication-title: IEEE Transactions on Image Processing
  doi: 10.1109/TIP.2021.3127850
– volume: 12
  start-page: 58
  issue: 1
  year: 1995
  ident: 2522_CR11
  publication-title: JOSA A
  doi: 10.1364/JOSAA.12.000058
– ident: 2522_CR8
  doi: 10.1109/CVPR52733.2024.02427
– ident: 2522_CR43
  doi: 10.1109/CVPR52733.2024.02273
– ident: 2522_CR42
  doi: 10.1007/978-3-642-15549-9_12
– ident: 2522_CR18
  doi: 10.1109/CVPR52729.2023.01753
– ident: 2522_CR28
  doi: 10.1109/CVPR52729.2023.00563
– ident: 2522_CR2
  doi: 10.1109/ICCV48922.2021.00229
– ident: 2522_CR9
– ident: 2522_CR38
  doi: 10.1109/CVPR52729.2023.00953
– ident: 2522_CR1
  doi: 10.1007/978-3-030-58607-2_7
– ident: 2522_CR34
  doi: 10.1109/CVPR.2015.7298665
– ident: 2522_CR33
  doi: 10.1007/978-3-319-24574-4_28
– ident: 2522_CR10
  doi: 10.1109/ICCV.2017.89
– ident: 2522_CR31
  doi: 10.1109/CVPR52729.2023.00557
– ident: 2522_CR45
  doi: 10.1109/CVPR46437.2021.01458
– ident: 2522_CR14
  doi: 10.1109/CVPR.2015.7298642
– ident: 2522_CR15
  doi: 10.1109/ICCV.2015.123
– volume: 111
  start-page: 257
  issue: 3
  year: 2023
  ident: 2522_CR54
  publication-title: Proceedings of the IEEE
  doi: 10.1109/JPROC.2023.3238524
– ident: 2522_CR17
  doi: 10.1109/CVPR46437.2021.00207
– volume: 13
  start-page: 600
  issue: 4
  year: 2004
  ident: 2522_CR40
  publication-title: IEEE transactions on image processing
  doi: 10.1109/TIP.2003.819861
– ident: 2522_CR16
– ident: 2522_CR32
  doi: 10.1109/ICCV51070.2023.01158
– ident: 2522_CR47
  doi: 10.1109/CVPR.2019.00613
– ident: 2522_CR7
  doi: 10.1109/ICCPHOT.2018.8368468
– ident: 2522_CR41
  doi: 10.1109/CVPR52688.2022.00475
SSID ssj0002823
Score 2.4819438
Snippet For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image...
For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Index Database
Publisher
StartPage 6953
SubjectTerms Artificial Intelligence
Blurring
Cameras
Computer Imaging
Computer Science
Datasets
Deep learning
Design
Effectiveness
Image acquisition
Image Processing and Computer Vision
Learning
Misalignment
Modules
Neural networks
Pattern Recognition
Pattern Recognition and Graphics
Source code
Supervision
Vision
Title Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs
URI https://link.springer.com/article/10.1007/s11263-025-02522-3
https://www.proquest.com/docview/3259951235
Volume 133
WOSCitedRecordID wos001524470700001&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: PRVAVX
  databaseName: SpringerLink Contemporary (1997 - Present)
  customDbUrl:
  eissn: 1573-1405
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002823
  issn: 0920-5691
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELagMLBQnqJQkAc2iJSH82KrgAIDVQUFsUXJ5VxVKilqWn4_58QmAsEAUyLnYll39vmz78XYKYRpSEADLQdEbIlQCivzM2mRroQApAQZ1MUmwsEgenmJhzoorDTe7sYkWWnqJtjNcSubo4oo9pUP-ipbo-0uUgUbHh6fP_UvHSLqAvJ0MPKD2NGhMj_38XU7ajDmN7Notdv02_8b5xbb1OiS9-rpsM1WsNhhbY00uV7HJTWZYg6mbZdJYvRU3QcWY-tmOckVPb1Pkd-9ks7hVyhnsCzpacgueI_r9Kxj3jdOXlzd7PL7SUkAf0w6nI90EQo-VKajPfbUvx5d3lq6CIMFbugurBwdAehH0sukH0CKAaAIU4Qoc1CgnUvICWMg4d7MBcxELKSNMhTgEdSzY2-ftYpZgQeM274bydzHXNhAf2Zx7gChB5HmKXEuszvszMgieatzbSRNVmXF1YQ4mlRcTbwO6xpxJXrdlYnnqgRqKv63w86NeJrPv_d2-DfyI7bhKglXXn1d1lrMl3jM1uF9MSnnJ9V8_AAD5dsk
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDLZ4SXDhjRgMyIEbVOojbVduCBibgGmCgbhVretMk2AguvH7cbqECQQHOLVK3SiyE-dL_AI4xDiLGWiQ46FMHBkr6eRhrhzWlRihUqiiSbGJuNNpPD4mXRMUVlpvd2uSrDT1NNjN8yubo44oDrUP-izMS96xdMb827uHT_3Lh4hJAXk-GIVR4plQmZ_7-LodTTHmN7Notds0V_43zlVYNuhSnE6mwxrM0HAdVgzSFGYdl9xkiznYtg1QzOgnfR847DuX40Gh6fn9iUT7mXWOOCf1guOSn5bsRJwKk561L5rWyUvom11xMygZ4PdZh4ueKUIhutp0tAn3zYveWcsxRRgc9GN_5BTkSaSwoYJchRFmFCHJOCNs5B5JcguFBWMMYtyb-0i5TKRyScUSA4Z6bhJswdzwZUjbINzQb6gipEK6yH_mSeEhoweZFRlzLndrcGRlkb5Ocm2k06zKmqspczStuJoGNahbcaVm3ZVp4OsEajr-twbHVjzTz7_3tvM38gNYbPVurtPrdudqF5Z8Le3Kw68Oc6O3Me3BAr6PBuXbfjU3PwBSvN4I
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3JTsMwEB2xCXFhR5TVB24QkcVJGm4VUEBAVYlF3KJkPK4qlYCalu9nnIUCggPilMhxLGvGHr_xbAAHGCYhAw2yHJSRJUMtrdRPtcWyEgPUGnVQFpsIO53m01PU_RTFX3i71ybJMqbBZGnKRsevSh9PAt8ct7A_muhi3_ijT8OsNI70Rl-_e_yQxaxQlMXkWUnyg8ipwmZ-HuPr0TTBm99MpMXJ0176_5yXYbFCnaJVLpMVmKJsFZYqBCqq_Z1zU13koW5bA80MGJh7wqxnXYz7yvTn9wGJq2eWReKM9AuOc37W3U5ES1RpW3uiXTt_CXPjK277OQP_Hst2cV8VpxBdY1Jah4f2-f3ppVUVZ7DQDd2RpciRSH5Te6n2A0woQJJhQthMHZJkK42KsQcxHk5dpFRGUtukQ4keQ0A78jZgJnvJaBOE7btNrXxS0kb-M42Ug4wqZKISplxqN-Cw5kv8WubgiCfZlg1VY6ZoXFA19hqwU7MurvZjHnuuSaxm4oIbcFSzavL599G2_tZ9H-a7Z-345qpzvQ0LrmF24fi3AzOj4Zh2YQ7fRv18uFcs03dhdubs
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=Reblurring-Guided+Single+Image+Defocus+Deblurring%3A+A+Learning+Framework+with+Misaligned+Training+Pairs&rft.jtitle=International+journal+of+computer+vision&rft.au=Ren%2C+Dongwei&rft.au=Shu%2C+Xinya&rft.au=Li%2C+Yu&rft.au=Wu%2C+Xiaohe&rft.date=2025-10-01&rft.pub=Springer+Nature+B.V&rft.issn=0920-5691&rft.eissn=1573-1405&rft.volume=133&rft.issue=10&rft.spage=6953&rft.epage=6970&rft_id=info:doi/10.1007%2Fs11263-025-02522-3&rft.externalDBID=HAS_PDF_LINK
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0920-5691&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0920-5691&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0920-5691&client=summon