Image super-resolution based on conditional generative adversarial network

Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high-frequency details. However, a mismatch between the input and the output may arise when GAN is directly applied to image super-resolution. To alleviate this issue, the authors adopte...

Full description

Saved in:
Bibliographic Details
Published in:IET image processing Vol. 14; no. 13; pp. 3006 - 3013
Main Authors: Gao, Hongxia, Chen, Zhanhong, Huang, Binyang, Chen, Jiahe, Li, Zhifu
Format: Journal Article
Language:English
Published: The Institution of Engineering and Technology 01.11.2020
Subjects:
ISSN:1751-9659, 1751-9667
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high-frequency details. However, a mismatch between the input and the output may arise when GAN is directly applied to image super-resolution. To alleviate this issue, the authors adopted a conditional GAN (cGAN) in this study. The cGAN discriminator attempted to guess whether the unknown high-resolution (HR) image was produced by the generator with the aid of the original low-resolution (LR) image. They propose a novel discriminator that only penalises at the scale of the patch and, thus, has relatively few parameters to train. The generator of cGAN is an encoder–decoder with skip connections to shuttle the shared low-level information directly across the network. To better maintain the low-frequency information and recover the high-frequency information, they designed a generator loss function combining adversarial loss term and L1 loss term. The former term is beneficial to the synthesis of fine-grained textures, while the latter is responsible for learning the overall structure of the LR input. The experiments revealed that the proposed method could generate HR images with richer details and less over-smoothness.
AbstractList Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high‐frequency details. However, a mismatch between the input and the output may arise when GAN is directly applied to image super‐resolution. To alleviate this issue, the authors adopted a conditional GAN (cGAN) in this study. The cGAN discriminator attempted to guess whether the unknown high‐resolution (HR) image was produced by the generator with the aid of the original low‐resolution (LR) image. They propose a novel discriminator that only penalises at the scale of the patch and, thus, has relatively few parameters to train. The generator of cGAN is an encoder–decoder with skip connections to shuttle the shared low‐level information directly across the network. To better maintain the low‐frequency information and recover the high‐frequency information, they designed a generator loss function combining adversarial loss term and L1 loss term. The former term is beneficial to the synthesis of fine‐grained textures, while the latter is responsible for learning the overall structure of the LR input. The experiments revealed that the proposed method could generate HR images with richer details and less over‐smoothness.
Author Chen, Zhanhong
Gao, Hongxia
Huang, Binyang
Chen, Jiahe
Li, Zhifu
Author_xml – sequence: 1
  givenname: Hongxia
  surname: Gao
  fullname: Gao, Hongxia
  organization: 1School of Automation Science and Engineering, South China University of Technology, Guangzhou 510000, People's Republic of China
– sequence: 2
  givenname: Zhanhong
  surname: Chen
  fullname: Chen, Zhanhong
  organization: 1School of Automation Science and Engineering, South China University of Technology, Guangzhou 510000, People's Republic of China
– sequence: 3
  givenname: Binyang
  surname: Huang
  fullname: Huang, Binyang
  email: scuthuangby@163.com
  organization: 1School of Automation Science and Engineering, South China University of Technology, Guangzhou 510000, People's Republic of China
– sequence: 4
  givenname: Jiahe
  surname: Chen
  fullname: Chen, Jiahe
  organization: 2School of Mechanical and Transportation Engineering, China University of Petroleum-Beijing, Beijing 102200, People's Republic of China
– sequence: 5
  givenname: Zhifu
  orcidid: 0000-0002-0382-7180
  surname: Li
  fullname: Li, Zhifu
  organization: 3School of Mechanical and Electric Engineering, Guangzhou University, Guangzhou 510000, People's Republic of China
BookMark eNqFkM1OAjEQgBuDiYA-gLd9gWK73d1uvSkRxJBojJ6bbjtLisuWtAuEt7cbjAcPeJrJZL75-UZo0LoWELqlZEJJJu4sdNhu_SQltJzkvOAXaEh5TrEoCj74zXNxhUYhrAnJBSnzIXpZbNQKkrDbgscegmt2nXVtUqkAJomJdq2xfUk1yQpa8Kqze0iU2YMPyttYbqE7OP91jS5r1QS4-Ylj9Dl7-pg-4-XrfDF9WGLNOM8xNVpwmgqWMlJzAQygJJxWTGeZqURBKqJVBqIwpKyZpqyuCsNqw3it482KjRE9zdXeheChlltvN8ofJSWylyGjDBllyF6G7GVEhv9htO1U_1bnlW3Okvcn8mAbOP6_Si7e3tPHGUlLmkcYn-C-be12PloMZ5Z9A9lCi4Q
CitedBy_id crossref_primary_10_1049_ipr2_12134
crossref_primary_10_1088_1742_6596_2634_1_012046
crossref_primary_10_1155_2022_1744969
crossref_primary_10_1371_journal_pone_0310594
Cites_doi 10.1109/CVPR.2017.19
10.1016/B978-012119792-6/50119-4
10.1109/CVPR.2016.182
10.1109/TIP.2017.2654163
10.1109/CVPR.2016.207
10.1109/TIP.2010.2050625
10.1109/TGRS.2018.2810208
10.1007/s00138-014-0623-4
10.1109/LGRS.2017.2736020
10.1109/CVPR.2018.00344
10.1109/CVPR.2018.00179
10.1109/LGRS.2016.2579661
10.1145/3343031.3351023
10.1109/CVPR.2016.278
10.1109/TPAMI.2015.2439281
10.1109/CVPR.2016.90
10.1007/978-3-319-46475-6_43
10.1109/TGRS.2012.2227329
10.1109/TGRS.2014.2307354
10.1109/ICCV.2013.75
10.1016/j.isprsjprs.2015.03.009
10.1007/978-3-319-10602-1_48
ContentType Journal Article
Copyright 2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology
Copyright_xml – notice: 2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology
DBID IDLOA
24P
AAYXX
CITATION
DOI 10.1049/iet-ipr.2018.5767
DatabaseName IET Digital Library Open Access
Wiley Online Library Open Access
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef


Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1751-9667
EndPage 3013
ExternalDocumentID 10_1049_iet_ipr_2018_5767
IPR2BF02815
Genre article
GrantInformation_xml – fundername: Fundamental Science and Technology Program of Guangzhou, China
  grantid: 201707010054
– fundername: National Natural Science Foundation of China
  grantid: 61603105
– fundername: Natural Science Foundation of Guangdong Province, China
  funderid: 2019A1515011041
– fundername: Fundamental Science and Technology Program of Guangzhou, China
  funderid: 201707010054
– fundername: National Natural Science Foundation of China
  funderid: 61603105
GroupedDBID 0R
24P
29I
4.4
5GY
6IK
8FE
8FG
8VB
AAJGR
ABJCF
ABPTK
ACGFS
ACIWK
AENEX
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ARAPS
BENPR
BFFAM
BGLVJ
CS3
DU5
EBS
EJD
ESX
HCIFZ
HZ
IDLOA
IFIPE
IPLJI
JAVBF
L6V
LAI
M43
M7S
MS
O9-
OCL
P2P
P62
PTHSS
QWB
RIE
RNS
RUI
S0W
UNR
ZL0
.DC
0R~
1OC
AAHHS
AAHJG
ABQXS
ACCFJ
ACCMX
ACESK
ACXQS
ADZOD
AEEZP
AEQDE
AIWBW
AJBDE
ALUQN
AVUZU
CCPQU
GROUPED_DOAJ
HZ~
IAO
ITC
K1G
MCNEO
MS~
OK1
ROL
AAMMB
AAYXX
AEFGJ
AFFHD
AGXDD
AIDQK
AIDYY
CITATION
PHGZM
PHGZT
PQGLB
WIN
ID FETCH-LOGICAL-c3775-1dc971293230f79e3ee8071b3c44db960b0ca4e96d08f3c13fb6d3fd37fc908a3
IEDL.DBID 24P
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000595800300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1751-9659
IngestDate Tue Nov 18 22:27:09 EST 2025
Wed Oct 29 21:21:49 EDT 2025
Wed Jan 22 16:30:25 EST 2025
Tue Jan 05 21:44:04 EST 2021
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 13
Keywords adversarial loss term
conditional GAN
high-frequency information
conditional generative adversarial network
high-resolution image
unsupervised learning
HR images
generator loss function
cGAN discriminator
L1 loss term
low-frequency information
image resolution
neural nets
image super-resolution
low-resolution image
Language English
License Attribution
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3775-1dc971293230f79e3ee8071b3c44db960b0ca4e96d08f3c13fb6d3fd37fc908a3
ORCID 0000-0002-0382-7180
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-ipr.2018.5767
PageCount 8
ParticipantIDs crossref_primary_10_1049_iet_ipr_2018_5767
iet_journals_10_1049_iet_ipr_2018_5767
wiley_primary_10_1049_iet_ipr_2018_5767_IPR2BF02815
crossref_citationtrail_10_1049_iet_ipr_2018_5767
ProviderPackageCode IDLOA
RUI
PublicationCentury 2000
PublicationDate 20201100
November 2020
2020-11-00
PublicationDateYYYYMMDD 2020-11-01
PublicationDate_xml – month: 11
  year: 2020
  text: 20201100
PublicationDecade 2020
PublicationTitle IET image processing
PublicationYear 2020
Publisher The Institution of Engineering and Technology
Publisher_xml – name: The Institution of Engineering and Technology
References Li, X.; Shen, H.; Zhang, L. (C2) 2014; 52
Wei, Y.; Yuan, Q.; Shen, H. (C15) 2017; 14
Nasrollahi, K.; Moeslund, B. (C1) 2014; 25
Dong, C.; Chen, C.L.; He, K. (C12) 2016; 38
Zhang, Z.; Li, F.; Zhao, M. (C10) 2017; 26
Li, J.; Yuan, Q.; Shen, H. (C6) 2016; 13
Zhang, Q.; Yuan, Q.; Zeng, C. (C14) 2016; 56
Li, X.; Shen, H.; Zhang, L. (C3) 2015; 106
Yang, J.; Wright, J.; Huang, T.S. (C5) 2010; 19
Lorenzi, L.; Melgani, F.; Mercier, G. (C7) 2013; 51
2017; 26
2010; 19
2017; 14
2013; 51
2008
2019
2014; 25
2018
2017
2016
2005
2015
2015; 106
2014
2013
2014; 52
2016; 38
2016; 13
2016; 56
Wang X. (e_1_2_6_22_1) 2016
e_1_2_6_10_1
e_1_2_6_31_1
e_1_2_6_30_1
Ioffe S. (e_1_2_6_24_1) 2015
e_1_2_6_19_1
e_1_2_6_13_1
e_1_2_6_14_1
e_1_2_6_11_1
e_1_2_6_12_1
Timofte R. (e_1_2_6_9_1) 2014
e_1_2_6_17_1
e_1_2_6_18_1
e_1_2_6_15_1
e_1_2_6_16_1
e_1_2_6_21_1
e_1_2_6_20_1
e_1_2_6_8_1
e_1_2_6_4_1
e_1_2_6_7_1
e_1_2_6_6_1
Denton E. (e_1_2_6_26_1) 2015
e_1_2_6_3_1
e_1_2_6_23_1
e_1_2_6_2_1
Yang J. (e_1_2_6_5_1) 2008
e_1_2_6_29_1
Goodfellow I.J. (e_1_2_6_25_1) 2014
e_1_2_6_28_1
e_1_2_6_27_1
References_xml – volume: 13
  start-page: 1250
  issue: 9
  year: 2016
  end-page: 1254
  ident: C6
  article-title: Hyperspectral image super-resolution by spectral mixture analysis and spatial–spectral group sparsity
  publication-title: IEEE Geosci. Remote Sens.
– volume: 14
  start-page: 1795
  issue: 10
  year: 2017
  end-page: 1799
  ident: C15
  article-title: Boosting the accuracy of multispectral image pan-sharpening by learning a deep residual network
  publication-title: IEEE Geosci. Remote Sens.
– volume: 52
  start-page: 7086
  issue: 11
  year: 2014
  end-page: 7098
  ident: C2
  article-title: Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 26
  start-page: 1607
  issue: 4
  year: 2017
  end-page: 1622
  ident: C10
  article-title: Robust neighborhood preserving projection by nuclear/L2, 1-norm regularization for image feature extraction
  publication-title: IEEE Trans. Image Process.
– volume: 56
  start-page: 4274
  issue: 8
  year: 2016
  end-page: 4288
  ident: C14
  article-title: Missing data reconstruction in remote sensing image with a unified spatial–temporal–spectral deep convolutional neural network
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 106
  start-page: 1
  year: 2015
  end-page: 15
  ident: C3
  article-title: Sparse-based reconstruction of missing information in remote sensing images from spectral/temporal complementary information
  publication-title: ISPRS J. Photogramm. Remote Sens.
– volume: 38
  start-page: 295
  issue: 2
  year: 2016
  ident: C12
  article-title: Image super-resolution using deep convolutional networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 19
  start-page: 2861
  issue: 11
  year: 2010
  end-page: 2873
  ident: C5
  article-title: Image super-resolution via sparse representation
  publication-title: IEEE Trans. Image Process.
– volume: 25
  start-page: 1423
  issue: 6
  year: 2014
  end-page: 1468
  ident: C1
  article-title: Super-resolution: a comprehensive survey
  publication-title: Mach. Vis. Appl.
– volume: 51
  start-page: 3998
  issue: 7
  year: 2013
  end-page: 4008
  ident: C7
  article-title: Missing-area reconstruction in multispectral images under a compressive sensing perspective
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 19
  start-page: 2861
  issue: 11
  year: 2010
  end-page: 2873
  article-title: Image super‐resolution via sparse representation
  publication-title: IEEE Trans. Image Process.
– start-page: 770
  year: 2016
  end-page: 778
– start-page: 18
  year: 2005
– start-page: 1664
  year: 2018
  end-page: 1673
– volume: 26
  start-page: 1607
  issue: 4
  year: 2017
  end-page: 1622
  article-title: Robust neighborhood preserving projection by nuclear/L2, 1‐norm regularization for image feature extraction
  publication-title: IEEE Trans. Image Process.
– volume: 25
  start-page: 1423
  issue: 6
  year: 2014
  end-page: 1468
  article-title: Super‐resolution: a comprehensive survey
  publication-title: Mach. Vis. Appl.
– volume: 51
  start-page: 3998
  issue: 7
  year: 2013
  end-page: 4008
  article-title: Missing‐area reconstruction in multispectral images under a compressive sensing perspective
  publication-title: IEEE Trans. Geosci. Remote Sens.
– year: 2016
– volume: 14
  start-page: 1795
  issue: 10
  year: 2017
  end-page: 1799
  article-title: Boosting the accuracy of multispectral image pan‐sharpening by learning a deep residual network
  publication-title: IEEE Geosci. Remote Sens.
– year: 2014
– volume: 52
  start-page: 7086
  issue: 11
  year: 2014
  end-page: 7098
  article-title: Recovering quantitative remote sensing products contaminated by thick clouds and shadows using multitemporal dictionary learning
  publication-title: IEEE Trans. Geosci. Remote Sens.
– start-page: 1874
  year: 2016
  end-page: 1883
– start-page: 3262
  year: 2018
  end-page: 3271
– volume: 56
  start-page: 4274
  issue: 8
  year: 2016
  end-page: 4288
  article-title: Missing data reconstruction in remote sensing image with a unified spatial–temporal–spectral deep convolutional neural network
  publication-title: IEEE Trans. Geosci. Remote Sens.
– start-page: 1
  year: 2008
  end-page: 8
– start-page: 561
  year: 2013
  end-page: 568
– start-page: 318
  year: 2016
  end-page: 335
– volume: 106
  start-page: 1
  year: 2015
  end-page: 15
  article-title: Sparse‐based reconstruction of missing information in remote sensing images from spectral/temporal complementary information
  publication-title: ISPRS J. Photogramm. Remote Sens.
– start-page: 694
  year: 2016
  end-page: 711
– start-page: 105
  year: 2017
  end-page: 114
– start-page: 2672
  year: 2014
  end-page: 2680
– start-page: 740
  year: 2014
  end-page: 755
– start-page: 2536
  year: 2016
  end-page: 2544
– volume: 13
  start-page: 1250
  issue: 9
  year: 2016
  end-page: 1254
  article-title: Hyperspectral image super‐resolution by spectral mixture analysis and spatial–spectral group sparsity
  publication-title: IEEE Geosci. Remote Sens.
– start-page: 448
  year: 2015
  end-page: 456
– volume: 38
  start-page: 295
  issue: 2
  year: 2016
  article-title: Image super‐resolution using deep convolutional networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 1486
  year: 2015
  end-page: 1494
– year: 2019
– start-page: 111
  year: 2014
  end-page: 126
– start-page: 1646
  year: 2016
  end-page: 1654
– ident: e_1_2_6_19_1
  doi: 10.1109/CVPR.2017.19
– ident: e_1_2_6_31_1
  doi: 10.1016/B978-012119792-6/50119-4
– ident: e_1_2_6_20_1
– ident: e_1_2_6_14_1
  doi: 10.1109/CVPR.2016.182
– start-page: 1486
  volume-title: Advances in Neural Information Processing Systems (NIPS)
  year: 2015
  ident: e_1_2_6_26_1
– ident: e_1_2_6_11_1
  doi: 10.1109/TIP.2017.2654163
– start-page: 1
  volume-title: Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
  year: 2008
  ident: e_1_2_6_5_1
– ident: e_1_2_6_18_1
  doi: 10.1109/CVPR.2016.207
– ident: e_1_2_6_28_1
– start-page: 318
  volume-title: Euro. Conf. on Computer Vision (ECCV)
  year: 2016
  ident: e_1_2_6_22_1
– ident: e_1_2_6_6_1
  doi: 10.1109/TIP.2010.2050625
– ident: e_1_2_6_15_1
  doi: 10.1109/TGRS.2018.2810208
– ident: e_1_2_6_2_1
  doi: 10.1007/s00138-014-0623-4
– ident: e_1_2_6_16_1
  doi: 10.1109/LGRS.2017.2736020
– ident: e_1_2_6_29_1
  doi: 10.1109/CVPR.2018.00344
– ident: e_1_2_6_30_1
  doi: 10.1109/CVPR.2018.00179
– ident: e_1_2_6_7_1
  doi: 10.1109/LGRS.2016.2579661
– ident: e_1_2_6_12_1
  doi: 10.1145/3343031.3351023
– start-page: 2672
  volume-title: Advances in Neural Information Processing Systems (NIPS)
  year: 2014
  ident: e_1_2_6_25_1
– ident: e_1_2_6_21_1
  doi: 10.1109/CVPR.2016.278
– ident: e_1_2_6_13_1
  doi: 10.1109/TPAMI.2015.2439281
– start-page: 448
  volume-title: Int. Conf. on Machine Learning (ICML)
  year: 2015
  ident: e_1_2_6_24_1
– ident: e_1_2_6_17_1
  doi: 10.1109/CVPR.2016.90
– ident: e_1_2_6_23_1
  doi: 10.1007/978-3-319-46475-6_43
– ident: e_1_2_6_8_1
  doi: 10.1109/TGRS.2012.2227329
– ident: e_1_2_6_3_1
  doi: 10.1109/TGRS.2014.2307354
– ident: e_1_2_6_10_1
  doi: 10.1109/ICCV.2013.75
– ident: e_1_2_6_4_1
  doi: 10.1016/j.isprsjprs.2015.03.009
– ident: e_1_2_6_27_1
  doi: 10.1007/978-3-319-10602-1_48
– start-page: 111
  volume-title: Asian Conf. on Computer Vision (ACCV)
  year: 2014
  ident: e_1_2_6_9_1
SSID ssj0059085
Score 2.2291758
Snippet Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high-frequency details. However, a mismatch...
Generative adversarial network (GAN) is one of the most prevalent generative models that can synthesise realistic high‐frequency details. However, a mismatch...
SourceID crossref
wiley
iet
SourceType Enrichment Source
Index Database
Publisher
StartPage 3006
SubjectTerms adversarial loss term
cGAN discriminator
conditional GAN
conditional generative adversarial network
generator loss function
high‐frequency information
high‐resolution image
HR images
image resolution
image super‐resolution
L1 loss term
low‐frequency information
low‐resolution image
neural nets
Research Article
unsupervised learning
Title Image super-resolution based on conditional generative adversarial network
URI http://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2018.5767
https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-ipr.2018.5767
Volume 14
WOSCitedRecordID wos000595800300006&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: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1751-9667
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0059085
  issn: 1751-9659
  databaseCode: WIN
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-9667
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0059085
  issn: 1751-9659
  databaseCode: 24P
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEF5a9eDFt1hf7EE8CNGku8kmRxWLhVKKKPYW9ikFraWpnv0J_kZ_iTObtFCECuIlhGQ3LLPz-GY3-w0hJxBRuTCxC5RLJJJqR0EqIxbAoJvgL5kJlWfX74huN-33s16NXE_PwpT8ELMFN7QM76_RwKUqq5AAqIVJHNhJMBghpWeUngNqFnWyHEVMoGo3eW_qjrGmd-xPRWI9-STOZlub2cWPT8wFpzq8noesPua01v9ltBtkrYKc9LLUkU1Ss8Mtsl7BT1oZd7FNOu0XcC60eBvZ8dfHJ-ThlVpSDHWGwg0kz2ZQrh7SJ09Yjd6SSqzqXEjUZTos_yvfIQ-tm_vr26AqthBoJkQcREZnAoM_5CROZJZZmwL8UExzbhTkOSrUktssMWHqmI6YU4lhzjDhNIhYsl2yNHwd2j1CpUxN6DhLjE24cmEmoHksYHKYForzBgmnUs51xUSOBTGec78jzrMcpJWDtHKUVo7SapCzWZdRScOxqPEpPquMsVjUkPk5-_2Tebt317xqARiL4v0_9Togq01M1f0xxkOyNBm_2SOyot8ng2J87FUWro_t7jcITPEK
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1JS8NAFH7UBfTiLu7OQTwI0aQzySRHt9JiLUUUvIVkFiloLU317E_wN_pLfG-SFkRQEG8hmRmGl7d9s3wP4AAjqpA6tF5uo4xItQMvzgLu4aTr6C-59nPHrt-WnU58f590a3AxvgtT8kNMFtzIMpy_JgOnBekScAoiyeyZkdcbEKdnEB9j2iynYEZgtKE6BnXRHftjKuodumuRVFA-CpPJ3mZy8m2IL9FpCj9_zVld0Gks_s90l2ChSjrZaakly1Az_RVYrBJQVpl3sQrt1hO6F1a8DMzw4-0dkXilmIyCnWb4gPBZ98r1Q_bgKKvJX7KM6joXGWkz65cny9fgrnF5e970qnILnuJShl6gVSIp_CMqsTIx3JgYE5CcKyF0jkgn91UmTBJpP7ZcBdzmkeZWc2kVyjjj6zDdf-6bDWBZFmvfCh5pE4nc-onE5qEMEBArmQuxCf5YzKmquMipJMZj6vbERZKitFKUVkrSSklam3A06TIoiTh-anxI7ypzLH5qyN1P-33ItNW9qZ81MB0Lwq0_9dqHuebtdTtttzpX2zBfJ-DuLjXuwPRo-GJ2YVa9jnrFcM_p7yeiYvPd
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1bS8MwFD54Q3xxXvFuHsQHodouadM-ehsOxxii4Ftpc5GBzrFuPvsT_I3-Es9Ju8EQFMS30iYhnJzblzTfATjCiCqkDq2X2ygjUu3Ai7OAezjpOvpLrv3cseu3ZLsdPz4mnRm4Gt-FKfkhJhtuZBnOX5OBm762JeAURJLZNUOv2ydOzyA-xbRZzsK8CNHXEr-z6Iz9MRX1Dt21SCooH4XJ5GwzOfs2xFR0msXP0zmrCzqN2v9MdwWWq6STnZdasgozprcGtSoBZZV5F-vQar6ge2HFqG8Gn-8fiMQrxWQU7DTDB4TPulvuH7InR1lN_pJlVNe5yEibWa_8s3wDHhrX95c3XlVuwVNcytALtEokhX9EJVYmhhsTYwKScyWEzhHp5L7KhEki7ceWq4DbPNLcai6tQhlnfBPmeq89swUsy2LtW8EjbSKRWz-R2ByXBgGxkrkQ2-CPxZyqioucSmI8p-5MXCQpSitFaaUkrZSktQ0nky79kojjp8bH9K4yx-Knhtwt2u9Dps3OXf2igelYEO78qdchLHauGmmr2b7dhaU64XZ3p3EP5oaDkdmHBfU27BaDA6e-X1gz82E
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+super%E2%80%90resolution+based+on+conditional+generative+adversarial+network&rft.jtitle=IET+image+processing&rft.au=Gao%2C+Hongxia&rft.au=Chen%2C+Zhanhong&rft.au=Huang%2C+Binyang&rft.au=Chen%2C+Jiahe&rft.date=2020-11-01&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=14&rft.issue=13&rft.spage=3006&rft.epage=3013&rft_id=info:doi/10.1049%2Fiet-ipr.2018.5767&rft.externalDBID=n%2Fa&rft.externalDocID=10_1049_iet_ipr_2018_5767
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon