Enhancing Border Learning for Better Image Denoising

Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematics (Basel) Ročník 13; číslo 7; s. 1119
Hlavní autoři: Ge, Xin, Zhu, Yu, Qi, Liping, Hu, Yaoqi, Sun, Jinqiu, Zhang, Yanning
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.04.2025
Témata:
ISSN:2227-7390, 2227-7390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at the borders of output images, referred to as border effects, which negatively impact the network’s ability to learn effective features. In traditional methods, these border effects, associated with convolutional/deconvolutional operations, have been mitigated using patch-based techniques. Inspired by this observation, patch-wise denoising algorithms were explored to derive a CNN architecture that avoids border effects. Specifically, we extend the patch-wise autoencoder to learn image mappings through patch extraction and patch-averaging operations, demonstrating that the patch-wise autoencoder is equivalent to a specific convolutional neural network (CNN) architecture, resulting in a novel residual block. This new residual block includes a mask that enhances the CNN’s ability to learn border features and eliminates border artifacts, referred to as the Border-Enhanced Residual Block (BERBlock). By stacking BERBlocks, we constructed a U-Net denoiser (BERUNet). Experiments on public datasets demonstrate that the proposed BERUNet achieves outstanding performance. The proposed network architecture is built on rigorous mathematical derivations, making its working mechanism highly interpretable. The code and all pretrained models are publicly available.
AbstractList Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply zero padding at the borders of input data to maintain consistent output dimensions. However, zero padding introduces ring-like artifacts at the borders of output images, referred to as border effects, which negatively impact the network’s ability to learn effective features. In traditional methods, these border effects, associated with convolutional/deconvolutional operations, have been mitigated using patch-based techniques. Inspired by this observation, patch-wise denoising algorithms were explored to derive a CNN architecture that avoids border effects. Specifically, we extend the patch-wise autoencoder to learn image mappings through patch extraction and patch-averaging operations, demonstrating that the patch-wise autoencoder is equivalent to a specific convolutional neural network (CNN) architecture, resulting in a novel residual block. This new residual block includes a mask that enhances the CNN’s ability to learn border features and eliminates border artifacts, referred to as the Border-Enhanced Residual Block (BERBlock). By stacking BERBlocks, we constructed a U-Net denoiser (BERUNet). Experiments on public datasets demonstrate that the proposed BERUNet achieves outstanding performance. The proposed network architecture is built on rigorous mathematical derivations, making its working mechanism highly interpretable. The code and all pretrained models are publicly available.
Audience Academic
Author Zhu, Yu
Ge, Xin
Sun, Jinqiu
Zhang, Yanning
Qi, Liping
Hu, Yaoqi
Author_xml – sequence: 1
  givenname: Xin
  orcidid: 0009-0003-0736-9468
  surname: Ge
  fullname: Ge, Xin
– sequence: 2
  givenname: Yu
  orcidid: 0000-0002-2480-0569
  surname: Zhu
  fullname: Zhu, Yu
– sequence: 3
  givenname: Liping
  surname: Qi
  fullname: Qi, Liping
– sequence: 4
  givenname: Yaoqi
  orcidid: 0009-0007-5809-6710
  surname: Hu
  fullname: Hu, Yaoqi
– sequence: 5
  givenname: Jinqiu
  surname: Sun
  fullname: Sun, Jinqiu
– sequence: 6
  givenname: Yanning
  orcidid: 0000-0002-2977-8057
  surname: Zhang
  fullname: Zhang, Yanning
BookMark eNptUUtPAjEQbgwmInLzB5B4Fexj2W2PgKgkJF703Mx2p1ACLXbLwX9vEWOIsT10Ot-jXzrXpOODR0JuGR0JoejDDtKaCVoxxtQF6XLOq2GVgc5ZfUX6bbuheSkmZKG6pJj7NXjj_GowDbHBOFgiRH-82xAHU0wp9xY7WOHgEX1wbYZuyKWFbYv9n7NH3p_mb7OX4fL1eTGbLIemoDINDdTWgGDIZEOpRSGlwcpwhDHwEmrDGynGNbNjTosqZ6qbuqYobFVnABvRI4uTbxNgo_fR7SB-6gBOfzdCXGmIyZktaiUNp0jBSiwLipVqDLNclRVQWyoss9fdyWsfw8cB26Q34RB9jq8Fk1KWSiieWaMTawXZ1HkbUgSTd4M7Z_KHW5f7EymkUJKKIgvuTwITQ9tGtL8xGdXHuejzuWQ6_0M3LkFywed33PZ_0ReF-5Gl
CitedBy_id crossref_primary_10_3390_rs17121994
crossref_primary_10_1016_j_knosys_2025_114230
Cites_doi 10.1016/j.engappai.2016.01.032
10.1109/CVPR46437.2021.01458
10.1109/CVPR52733.2024.02454
10.1145/1390156.1390294
10.1109/ICIP.2019.8803537
10.1016/j.neunet.2018.07.016
10.1109/CVPR52733.2024.02380
10.1007/s41365-023-01208-0
10.3390/math11081777
10.1109/TITS.2023.3259003
10.1109/TMM.2024.3407656
10.1109/CVPRW50498.2020.00270
10.1109/CVPRW.2017.151
10.3389/fams.2022.995225
10.1109/TIP.2016.2631888
10.1109/CVPR.2019.00223
10.1109/ISCAS48785.2022.9937486
10.1109/ICCV.2011.6126278
10.1007/s11263-024-02069-9
10.1109/TIP.2006.881969
10.1109/ASAP.2017.7995254
10.1109/TIP.2020.2971346
10.1016/j.patcog.2016.06.008
10.1109/ICMLA58977.2023.00040
10.1109/CVPR42600.2020.00277
10.1109/CVPR52733.2024.00268
10.1109/ICCVW60793.2023.00017
10.1109/CVPR.2016.90
10.1016/j.patcog.2023.109432
10.1109/TIP.2017.2662206
10.1109/CVPR.2012.6247952
10.1109/ICME55011.2023.00470
10.1109/CVPR52733.2024.02628
10.1109/CVPR.2014.366
10.1109/TIP.2012.2235847
10.1109/SAUS61785.2024.10563715
10.1109/TIP.2016.2541318
10.1109/ICCV48922.2021.00429
10.1109/CVPR.2017.528
10.1109/CVPR.2015.7299156
10.1109/ICCV.2017.486
10.1016/j.neunet.2019.08.022
10.1016/j.inffus.2023.102043
10.1109/CVPR52733.2024.00292
10.1109/CVPRW53098.2021.00027
10.1109/ICCV.2015.123
10.1016/j.patcog.2024.110815
10.1109/TIP.2010.2042098
10.1007/s11263-023-01852-4
10.1109/ICCVW60793.2023.00430
10.1117/1.3600632
10.1002/cpa.20042
10.1109/CVPR.2017.300
10.1088/1361-6560/acc000
10.1109/TIP.2018.2839891
10.1016/j.knosys.2024.112130
10.1109/TPAMI.2021.3088914
10.1155/2023/8342104
10.1109/TPAMI.2022.3167175
10.1016/j.patcog.2024.110291
10.1016/j.optlaseng.2024.108684
10.1109/CVPR.2005.160
10.1109/CVPR.2018.00333
10.1109/ICCVW54120.2021.00210
10.1142/S021946782550072X
10.1109/CVPR46437.2021.00069
10.1109/TSMC.2024.3429345
10.1109/CVPR.2018.00182
10.1109/TIP.2022.3181488
10.1109/TCSVT.2022.3170689
10.1109/TSP.2006.881199
10.1109/CVPR52688.2022.00564
10.1109/TNNLS.2018.2838679
10.1109/ICCV.2015.178
10.1109/ICIAS49414.2021.9642661
10.1016/j.engappai.2023.106048
10.1109/CVPR52688.2022.01688
10.1109/ICCV.2001.937655
10.1109/TIP.2021.3090531
ContentType Journal Article
Copyright COPYRIGHT 2025 MDPI AG
2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: COPYRIGHT 2025 MDPI AG
– notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID AAYXX
CITATION
3V.
7SC
7TB
7XB
8AL
8FD
8FE
8FG
8FK
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FR3
GNUQQ
HCIFZ
JQ2
K7-
KR7
L6V
L7M
L~C
L~D
M0N
M7S
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PTHSS
Q9U
DOA
DOI 10.3390/math13071119
DatabaseTitle CrossRef
Publicly Available Content Database
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
Mechanical & Transportation Engineering Abstracts
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Engineering Collection
Advanced Technologies & Aerospace Collection
Civil Engineering Abstracts
ProQuest Computing
Engineering Database
ProQuest Central Basic
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
DatabaseTitleList Publicly Available Content Database

CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
EISSN 2227-7390
ExternalDocumentID oai_doaj_org_article_98c20e0af8e640e79dc1f2967a0f69e6
A838398034
10_3390_math13071119
GeographicLocations United States
New Jersey
GeographicLocations_xml – name: New Jersey
– name: United States
GroupedDBID -~X
5VS
85S
8FE
8FG
AADQD
AAFWJ
AAYXX
ABDBF
ABJCF
ABPPZ
ABUWG
ACIPV
ACIWK
ADBBV
AFFHD
AFKRA
AFPKN
AFZYC
ALMA_UNASSIGNED_HOLDINGS
AMVHM
ARAPS
AZQEC
BCNDV
BENPR
BGLVJ
BPHCQ
CCPQU
CITATION
DWQXO
GNUQQ
GROUPED_DOAJ
HCIFZ
IAO
ITC
K6V
K7-
KQ8
L6V
M7S
MODMG
M~E
OK1
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PROAC
PTHSS
RNS
3V.
7SC
7TB
7XB
8AL
8FD
8FK
FR3
JQ2
KR7
L7M
L~C
L~D
M0N
P62
PKEHL
PQEST
PQUKI
Q9U
ID FETCH-LOGICAL-c408t-cabfca31e18d00fe388ce7c2ea5a26abc2d835b1f52047009bdbb0e3f7bd83ed3
IEDL.DBID M7S
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001463892800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2227-7390
IngestDate Mon Nov 10 04:32:54 EST 2025
Fri Jul 25 11:59:36 EDT 2025
Tue Nov 04 18:12:06 EST 2025
Tue Nov 18 21:55:15 EST 2025
Sat Nov 29 07:14:08 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c408t-cabfca31e18d00fe388ce7c2ea5a26abc2d835b1f52047009bdbb0e3f7bd83ed3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0009-0003-0736-9468
0000-0002-2977-8057
0000-0002-2480-0569
0009-0007-5809-6710
OpenAccessLink https://www.proquest.com/docview/3188869392?pq-origsite=%requestingapplication%
PQID 3188869392
PQPubID 2032364
ParticipantIDs doaj_primary_oai_doaj_org_article_98c20e0af8e640e79dc1f2967a0f69e6
proquest_journals_3188869392
gale_infotracacademiconefile_A838398034
crossref_primary_10_3390_math13071119
crossref_citationtrail_10_3390_math13071119
PublicationCentury 2000
PublicationDate 2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationPlace Basel
PublicationPlace_xml – name: Basel
PublicationTitle Mathematics (Basel)
PublicationYear 2025
Publisher MDPI AG
Publisher_xml – name: MDPI AG
References Majumdar (ref_59) 2018; 106
ref_94
ref_92
Herbreteau (ref_47) 2022; 31
ref_91
ref_90
ref_14
ref_11
ref_99
ref_98
ref_97
ref_96
ref_95
Ning (ref_38) 2023; 121
Elad (ref_42) 2006; 15
Islam (ref_26) 2024; 132
ref_18
ref_17
ref_15
Tian (ref_86) 2024; 54
ref_25
ref_22
ref_21
ref_20
Yan (ref_8) 2020; 29
ref_29
Daubechies (ref_62) 2004; 57
ref_28
ref_27
ref_70
Ma (ref_72) 2016; 26
ref_79
ref_78
Dong (ref_45) 2012; 22
ref_76
ref_74
ref_73
Aharon (ref_43) 2006; 54
Zhang (ref_77) 2011; 20
Xu (ref_31) 2010; 19
Bhatti (ref_48) 2023; 2023
ref_83
ref_82
ref_81
ref_80
Zhang (ref_51) 2016; 50
Martin (ref_71) 2001; Volume 2
Wu (ref_5) 2024; 26
ref_87
Tian (ref_89) 2020; 121
ref_84
Chen (ref_101) 2024; 132
ref_50
Liu (ref_41) 2023; 45
Zhang (ref_88) 2018; 27
Zhang (ref_4) 2021; 44
ref_57
ref_56
ref_54
Wu (ref_3) 2024; 149
ref_53
Zhang (ref_1) 2017; 26
ref_52
Hu (ref_23) 2024; 300
Niu (ref_19) 2024; 156
ref_61
ref_69
ref_68
ref_67
ref_66
Liu (ref_10) 2025; 184
ref_65
ref_64
ref_63
Tian (ref_85) 2024; 102
Zhang (ref_13) 2023; 34
Xu (ref_16) 2022; 32
Scetbon (ref_32) 2021; 30
ref_36
ref_35
ref_34
ref_33
Lin (ref_24) 2024; 62
ref_30
Zamir (ref_93) 2022; 45
ref_39
ref_37
Yan (ref_12) 2023; 138
Wang (ref_60) 2016; 25
ref_46
ref_44
ref_100
ref_40
ref_2
Roth (ref_75) 2005; Volume 2
Majumdar (ref_55) 2018; 30
ref_49
Lore (ref_58) 2017; 61
ref_9
ref_7
ref_6
References_xml – volume: 50
  start-page: 245
  year: 2016
  ident: ref_51
  article-title: Deep neural network for halftone image classification based on sparse auto-encoder
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2016.01.032
– ident: ref_92
  doi: 10.1109/CVPR46437.2021.01458
– ident: ref_68
– ident: ref_39
– ident: ref_6
  doi: 10.1109/CVPR52733.2024.02454
– ident: ref_52
  doi: 10.1145/1390156.1390294
– ident: ref_37
  doi: 10.1109/ICIP.2019.8803537
– volume: 106
  start-page: 271
  year: 2018
  ident: ref_59
  article-title: Graph structured autoencoder
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2018.07.016
– ident: ref_97
  doi: 10.1109/CVPR52733.2024.02380
– volume: 34
  start-page: 61
  year: 2023
  ident: ref_13
  article-title: Hformer: Highly efficient vision transformer for low-dose CT denoising
  publication-title: Nucl. Sci. Tech.
  doi: 10.1007/s41365-023-01208-0
– ident: ref_100
  doi: 10.3390/math11081777
– volume: 45
  start-page: 6096
  year: 2023
  ident: ref_41
  article-title: Partial convolution for padding, inpainting, and image synthesis
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TITS.2023.3259003
– volume: 26
  start-page: 10381
  year: 2024
  ident: ref_5
  article-title: RUN: Rethinking the UNet Architecture for Efficient Image Restoration
  publication-title: IEEE Trans. Multimed.
  doi: 10.1109/TMM.2024.3407656
– ident: ref_33
  doi: 10.1109/CVPRW50498.2020.00270
– ident: ref_73
  doi: 10.1109/CVPRW.2017.151
– ident: ref_80
  doi: 10.3389/fams.2022.995225
– volume: 26
  start-page: 1004
  year: 2016
  ident: ref_72
  article-title: Waterloo exploration database: New challenges for image quality assessment models
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2016.2631888
– ident: ref_98
  doi: 10.1109/CVPR.2019.00223
– ident: ref_70
  doi: 10.1109/ISCAS48785.2022.9937486
– ident: ref_30
  doi: 10.1109/ICCV.2011.6126278
– volume: 132
  start-page: 3889
  year: 2024
  ident: ref_26
  article-title: Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-024-02069-9
– volume: 15
  start-page: 3736
  year: 2006
  ident: ref_42
  article-title: Image denoising via sparse and redundant representations over learned dictionaries
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2006.881969
– ident: ref_63
  doi: 10.1109/ASAP.2017.7995254
– volume: 29
  start-page: 4308
  year: 2020
  ident: ref_8
  article-title: Deep HDR imaging via a non-local network
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2020.2971346
– volume: 61
  start-page: 650
  year: 2017
  ident: ref_58
  article-title: LLNet: A deep autoencoder approach to natural low-light image enhancement
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2016.06.008
– ident: ref_40
  doi: 10.1109/ICMLA58977.2023.00040
– ident: ref_90
  doi: 10.1109/CVPR42600.2020.00277
– ident: ref_22
  doi: 10.1109/CVPR52733.2024.00268
– ident: ref_27
  doi: 10.1109/ICCVW60793.2023.00017
– ident: ref_65
  doi: 10.1109/CVPR.2016.90
– volume: 138
  start-page: 109432
  year: 2023
  ident: ref_12
  article-title: 3D Medical image segmentation using parallel transformers
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2023.109432
– volume: 26
  start-page: 3142
  year: 2017
  ident: ref_1
  article-title: Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2662206
– ident: ref_53
  doi: 10.1109/CVPR.2012.6247952
– ident: ref_94
  doi: 10.1109/ICME55011.2023.00470
– ident: ref_21
  doi: 10.1109/CVPR52733.2024.02628
– ident: ref_44
  doi: 10.1109/CVPR.2014.366
– ident: ref_25
– volume: 22
  start-page: 1620
  year: 2012
  ident: ref_45
  article-title: Nonlocally centralized sparse representation for image restoration
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2012.2235847
– ident: ref_50
– ident: ref_56
  doi: 10.1109/SAUS61785.2024.10563715
– volume: 25
  start-page: 2117
  year: 2016
  ident: ref_60
  article-title: Non-local auto-encoder with collaborative stabilization for image restoration
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2016.2541318
– ident: ref_81
– ident: ref_84
  doi: 10.1109/ICCV48922.2021.00429
– ident: ref_61
  doi: 10.1109/CVPR.2017.528
– ident: ref_78
  doi: 10.1109/CVPR.2015.7299156
– ident: ref_2
  doi: 10.1109/ICCV.2017.486
– ident: ref_64
– volume: 121
  start-page: 461
  year: 2020
  ident: ref_89
  article-title: Image denoising using deep CNN with batch renormalization
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2019.08.022
– ident: ref_36
– volume: 102
  start-page: 102043
  year: 2024
  ident: ref_85
  article-title: A cross Transformer for image denoising
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2023.102043
– ident: ref_95
– ident: ref_99
  doi: 10.1109/CVPR52733.2024.00292
– ident: ref_91
  doi: 10.1109/CVPRW53098.2021.00027
– ident: ref_83
  doi: 10.1109/ICCV.2015.123
– volume: 156
  start-page: 110815
  year: 2024
  ident: ref_19
  article-title: Gr-gan: A unified adversarial framework for single image glare removal and denoising
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2024.110815
– volume: 19
  start-page: 1153
  year: 2010
  ident: ref_31
  article-title: Image inpainting by patch propagation using patch sparsity
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2010.2042098
– volume: 132
  start-page: 208
  year: 2024
  ident: ref_101
  article-title: Context autoencoder for self-supervised representation learning
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-023-01852-4
– ident: ref_35
– ident: ref_28
  doi: 10.1109/ICCVW60793.2023.00430
– volume: 20
  start-page: 023016
  year: 2011
  ident: ref_77
  article-title: Color demosaicking by local directional interpolation and nonlocal adaptive thresholding
  publication-title: J. Electron. Imaging
  doi: 10.1117/1.3600632
– volume: 57
  start-page: 1413
  year: 2004
  ident: ref_62
  article-title: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
  publication-title: Commun. Pure Appl. Math. J. Issued Courant Inst. Math. Sci.
  doi: 10.1002/cpa.20042
– ident: ref_87
  doi: 10.1109/CVPR.2017.300
– ident: ref_49
  doi: 10.1088/1361-6560/acc000
– volume: 27
  start-page: 4608
  year: 2018
  ident: ref_88
  article-title: FFDNet: Toward a fast and flexible solution for CNN-based image denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2018.2839891
– volume: 300
  start-page: 112130
  year: 2024
  ident: ref_23
  article-title: Dynamic center point learning for multiple object tracking under Severe occlusions
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2024.112130
– volume: 44
  start-page: 6360
  year: 2021
  ident: ref_4
  article-title: Plug-and-play image restoration with deep denoiser prior
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2021.3088914
– volume: 2023
  start-page: 8342104
  year: 2023
  ident: ref_48
  article-title: Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence
  publication-title: Int. J. Intell. Syst.
  doi: 10.1155/2023/8342104
– volume: 45
  start-page: 1934
  year: 2022
  ident: ref_93
  article-title: Learning enriched features for fast image restoration and enhancement
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2022.3167175
– volume: 149
  start-page: 110291
  year: 2024
  ident: ref_3
  article-title: Dual residual attention network for image denoising
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2024.110291
– ident: ref_17
– volume: 184
  start-page: 108684
  year: 2025
  ident: ref_10
  article-title: Polarimetric image denoising via non-local based cube matching convolutional neural network
  publication-title: Opt. Lasers Eng.
  doi: 10.1016/j.optlaseng.2024.108684
– volume: Volume 2
  start-page: 860
  year: 2005
  ident: ref_75
  article-title: Fields of experts: A framework for learning image priors
  publication-title: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05)
  doi: 10.1109/CVPR.2005.160
– ident: ref_20
– ident: ref_96
  doi: 10.1109/CVPR.2018.00333
– ident: ref_7
– ident: ref_11
  doi: 10.1109/ICCVW54120.2021.00210
– ident: ref_76
– ident: ref_9
  doi: 10.1142/S021946782550072X
– ident: ref_34
– ident: ref_14
  doi: 10.1109/CVPR46437.2021.00069
– volume: 54
  start-page: 6621
  year: 2024
  ident: ref_86
  article-title: Heterogeneous window transformer for image denoising
  publication-title: IEEE Trans. Syst. Man Cybern. Syst.
  doi: 10.1109/TSMC.2024.3429345
– ident: ref_82
– ident: ref_74
  doi: 10.1109/CVPR.2018.00182
– volume: 62
  start-page: 1
  year: 2024
  ident: ref_24
  article-title: Motion-aware correlation filter-based object tracking in satellite videos
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 31
  start-page: 4292
  year: 2022
  ident: ref_47
  article-title: DCT2net: An interpretable shallow CNN for image denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2022.3181488
– volume: 32
  start-page: 6530
  year: 2022
  ident: ref_16
  article-title: Deep sparse representation based image restoration with denoising prior
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2022.3170689
– ident: ref_18
– volume: 54
  start-page: 4311
  year: 2006
  ident: ref_43
  article-title: K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation
  publication-title: IEEE Trans. Signal Process.
  doi: 10.1109/TSP.2006.881199
– ident: ref_69
  doi: 10.1109/CVPR52688.2022.00564
– ident: ref_79
– ident: ref_29
– ident: ref_54
– volume: 30
  start-page: 312
  year: 2018
  ident: ref_55
  article-title: Blind denoising autoencoder
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2018.2838679
– ident: ref_46
– ident: ref_66
  doi: 10.1109/ICCV.2015.178
– ident: ref_67
  doi: 10.1109/ICIAS49414.2021.9642661
– ident: ref_57
– volume: 121
  start-page: 106048
  year: 2023
  ident: ref_38
  article-title: Learning-based padding: From connectivity on data borders to data padding
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.106048
– ident: ref_15
  doi: 10.1109/CVPR52688.2022.01688
– volume: Volume 2
  start-page: 416
  year: 2001
  ident: ref_71
  article-title: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
  publication-title: Proceedings of the Eighth IEEE International Conference on Computer Vision, ICCV 2001
  doi: 10.1109/ICCV.2001.937655
– volume: 30
  start-page: 5944
  year: 2021
  ident: ref_32
  article-title: Deep k-svd denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3090531
SSID ssj0000913849
Score 2.3008678
Snippet Deep neural networks for image denoising typically follow an encoder–decoder model, with convolutional (Conv) layers as essential components. Conv layers apply...
SourceID doaj
proquest
gale
crossref
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
StartPage 1119
SubjectTerms Accuracy
Algorithms
Analysis
Artificial neural networks
autoencoder
border effect
Borders
convolutional neural network
Deep learning
Design
image denoising
Machine learning
Neural networks
Noise reduction
padding
patch-based method
Title Enhancing Border Learning for Better Image Denoising
URI https://www.proquest.com/docview/3188869392
https://doaj.org/article/98c20e0af8e640e79dc1f2967a0f69e6
Volume 13
WOSCitedRecordID wos001463892800001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: K7-
  dateStart: 20130301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: M7S
  dateStart: 20130301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: BENPR
  dateStart: 20130301
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2227-7390
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000913849
  issn: 2227-7390
  databaseCode: PIMPY
  dateStart: 20130301
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LbxMxELag5QAH3hWBEu0BxAFZ9Xq9a_uEGkhFhRpFPKRysvwYp5Vg0yYpR347Y8cJcCgXLj6sffDOeJ4ef0PIi876NqAnT1sPjKKFUNTW1lPXgnWok1kXXW42IScTdXqqpyXhtixllRudmBV1mPuUIz_As6dUp9Gcv7m4pKlrVLpdLS00bpLdhJJQ59K9T9scS8K8VEKv690bjO4P0As8Q60tUcL1X5YoA_Zfp5azrTm697-7vE_uFi-zOlwfiwfkBvQPyZ2TLUTr8hER4_4sYW30s2qU8TerArU6q9CPrUb5mU91_B31TfUO-vl5Sio8Jl-Oxp_fvqelhQL1gqkV9dZFb5saahUYi9Ao5UF6Dra1vLPO84AumKtjy5mQSDAXnGPQROlwAkKzR3b6eQ9PSBVcw6XtoLbMi1gHBY1wouWSY3COQeWAvN6Q0_iCL57aXHwzGGck4ps_iT8gL7erL9a4GtesGyXObNckNOz8Yb6YmSJcRivPGTAbFXSCgdTB15HrTloWOw24tVeJrybJLG7J2_L0AH8soV-ZQ4VxulasEQOyv-GrKcK8NL-Z-vTf08_IbZ7aA-fCnn2ys1pcwXNyy_9YnS8XQ7I7Gk-mH4c57Mfxg6TDfF7T-HOM89Pjk-nXXwP69NE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VggQ98FnUhQI5UHFAUR3biZ0DQl3aqqttVxyK1Jvxx2RbCbLt7hbEn-pv7DibLHAotx64xlbkZJ7fvDj2G4C3hfV5ICWf5h5ZShlCpzazPnU5WkeczIrKNcUm1GikT07Kzytw1Z2FidsqO05siDpMfFwj3ybsaV2UlM4_nl-ksWpU_LvaldBYwGKIv37SJ9vsw2CX4rvF-f7e8aeDtK0qkHrJ9Dz11lXeigwzHRirUGjtUXmONre8sM7zQKrEZVXOmVQkQVxwjqGolKMGDILuewfuSqFVnFdDlS7XdKLHppblYn-9ECXbJtV5SllCEaOUf2W-pkDATWmgyW37j_63t_IYHrYqOtlZwP4JrGD9FNaOlha0s2cg9-rT6CVSj5N-4y-atFay44R0etJvjjElg-_Ep8ku1pOzuGiyDl9uZdjPYbWe1LgBSXCCK1tgZpmXVRY0CulkzhVHRxqo6MH7LnzGt_7psYzHN0PfUTHY5s9g92Br2ft84RtyQ79-RMKyT3T7bi5MpmPTkocptecMma00FpKhKoPPKl4WyrKqKJGG9i7iyEROoiF52x6toAeL7l5mRwvSwZoJ2YPNDkemJauZ-Q2iF_9ufgP3D46PDs3hYDR8CQ94LIXcbGLahNX59BJfwT3_Y342m75u5kUCX28bctclZ08W
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3Pb9MwFH4aHUJw4OfQOgbkwMQBRXVsJ3EOCK10FdVY1QNI42Rs57mbBOnWliH-tf11e06TAodx24FrbEVO_Pl7X5zn7wG8yoxLS1LyceqQxRQhVGwS42KborHEySzzti42kY_H6vi4mGzAZXsWJqRVtpxYE3U5c2GPvEfYUyorKJz3fJMWMRkM352dx6GCVPjT2pbTWEHkEH_9pM-3xdvRgOZ6j_Phwaf3H-KmwkDsJFPL2BnrnREJJqpkzKNQymHuOJrU8MxYx0tSKDbxKWcyJzliS2sZCp9basBS0H1vwSZJcsk7sDkZHU2-rHd4guOmksUq216IgvVIg55QzMiJX4q_4mBdLuC6oFBHuuGD__kdPYT7jb6O9lcL4hFsYPUY7h2tzWkXT0AeVCfBZaSaRv3aeTRqTGanESn4qF8fcIpG34lpowFWs9OwnbIFn29k2E-hU80q3IaotILnJsPEMCd9UioU0sqU5xwtqaOsC2_aqdSucVYPBT6-afrCChOv_5z4Luyte5-tHEWu6dcPqFj3CT7g9YXZfKobWtGFcpwhM15hJhnmRekSz4ssN8xnBdLQXgdM6cBWNCRnmkMX9GDB90vvK0EKWTEhu7DbYko3NLbQvwG18-_ml3CHkKY_jsaHz-AuDzWS6-ymXegs5z_wOdx2F8vTxfxFs0gi-HrTmLsC9YhZlw
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=Enhancing+Border+Learning+for+Better+Image+Denoising&rft.jtitle=Mathematics+%28Basel%29&rft.au=Ge%2C+Xin&rft.au=Zhu%2C+Yu&rft.au=Qi%2C+Liping&rft.au=Hu%2C+Yaoqi&rft.date=2025-04-01&rft.issn=2227-7390&rft.eissn=2227-7390&rft.volume=13&rft.issue=7&rft.spage=1119&rft_id=info:doi/10.3390%2Fmath13071119&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_math13071119
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2227-7390&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2227-7390&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2227-7390&client=summon