RGPNet: Learning a detail-preserved progressive model for single image deraining based on gradient prior

The issue of rain removal in images is challenging due to the diverse rain distributions and complex backgrounds. Although deraining capabilities have greatly improved in the previous single-stage approaches, background detail loss is a common result. To effectively remove rain that is diversly dist...

Full description

Saved in:
Bibliographic Details
Published in:Digital signal processing Vol. 165; p. 105312
Main Authors: Luo, Yu, Liang, Gaoquan, Ling, Jie, Zhou, Teng, Huang, Huiwu, Han, Tian
Format: Journal Article
Language:English
Published: Elsevier Inc 01.10.2025
Subjects:
ISSN:1051-2004
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The issue of rain removal in images is challenging due to the diverse rain distributions and complex backgrounds. Although deraining capabilities have greatly improved in the previous single-stage approaches, background detail loss is a common result. To effectively remove rain that is diversly distributed, many methods adopt a multistage rain removal framework for progressive deraining. Most of these multistage methods repeatedly use information from previous stages, or the original rainy image to refine the rain extracted from the background, leading to high demands on the ability to discriminate the background structure from the rain. To address this problem, we introduce a gradient prior to artificially preserve the background details. In addition, an attention LSTM is proposed to reduce the artifacts caused by over-deraining, by focusing on the more visible rain regions. The overall architecture of the proposed method consists of a rain streak extraction branch and a background detail recovery branch, with the designed attention LSTM and the proposed gradient prior integrated into the former and latter branches, respectively. Experiments on several well-known benchmark datasets show that our methods can outperform many state-of-the-art methods.
AbstractList The issue of rain removal in images is challenging due to the diverse rain distributions and complex backgrounds. Although deraining capabilities have greatly improved in the previous single-stage approaches, background detail loss is a common result. To effectively remove rain that is diversly distributed, many methods adopt a multistage rain removal framework for progressive deraining. Most of these multistage methods repeatedly use information from previous stages, or the original rainy image to refine the rain extracted from the background, leading to high demands on the ability to discriminate the background structure from the rain. To address this problem, we introduce a gradient prior to artificially preserve the background details. In addition, an attention LSTM is proposed to reduce the artifacts caused by over-deraining, by focusing on the more visible rain regions. The overall architecture of the proposed method consists of a rain streak extraction branch and a background detail recovery branch, with the designed attention LSTM and the proposed gradient prior integrated into the former and latter branches, respectively. Experiments on several well-known benchmark datasets show that our methods can outperform many state-of-the-art methods.
ArticleNumber 105312
Author Zhou, Teng
Huang, Huiwu
Liang, Gaoquan
Ling, Jie
Han, Tian
Luo, Yu
Author_xml – sequence: 1
  givenname: Yu
  surname: Luo
  fullname: Luo, Yu
  email: yuluo@gdut.edu.cn
  organization: School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, Guangdong province, China
– sequence: 2
  givenname: Gaoquan
  orcidid: 0009-0009-7236-8721
  surname: Liang
  fullname: Liang, Gaoquan
  email: lianggaoquan@gmail.com
  organization: School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, Guangdong province, China
– sequence: 3
  givenname: Jie
  surname: Ling
  fullname: Ling, Jie
  email: jling@gdut.edu.cn
  organization: School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, Guangdong province, China
– sequence: 4
  givenname: Teng
  surname: Zhou
  fullname: Zhou, Teng
  email: teng.zhou@hainanu.edu.cn
  organization: School of Cyberspace Security (School of Cryptology), Hainan University, Haikou, 570228, Hainan province, China
– sequence: 5
  givenname: Huiwu
  orcidid: 0009-0000-2626-2998
  surname: Huang
  fullname: Huang, Huiwu
  email: hedy@gdut.edu.cn
  organization: School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, 510006, Guangdong province, China
– sequence: 6
  givenname: Tian
  surname: Han
  fullname: Han, Tian
  email: than6@stevens.edu
  organization: Department of Computer Science, Stevens Institute of Technology, Hoboken, 07030, NJ, United States
BookMark eNp9kM9KAzEQh3OoYFt9AG95ga35s8laPUnRKhQV0XPIJpM1Zbspk6Xg25taz55mBuab-fHNyGRIAxByxdmCM66vtwuf9wvBhCqzklxMyLQ0vBKM1edklvOWMdbUQk_J1_v67QXGW7oBi0McOmqph9HGvtojZMADeLrH1JUhxwPQXfLQ05CQ5rLdA40720Fh0MZfvrW5IGmgHVofYRgLHhNekLNg-wyXf3VOPh8fPlZP1eZ1_by631ROKD5Wbllr8ApEC0LUHLzV7Y1XTi5D2wATwKV2PoAV4INSUkvNbFOzAEwvG-nknPDTXYcpZ4RgyvudxW_DmTnqMVtT9JijHnPSU5i7EwMl2CECmuxKcgc-IrjR-BT_oX8AbqFzHw
Cites_doi 10.1016/j.cviu.2020.103106
10.1109/TIP.2021.3074804
10.1109/TIP.2011.2179057
10.1016/j.vrih.2022.06.002
10.1109/TCSVT.2019.2920407
10.1016/j.cviu.2023.103766
10.1016/j.cogr.2024.12.002
10.1016/j.cviu.2023.103657
10.1016/j.apm.2018.03.001
10.1109/TIP.2017.2691802
10.1016/j.patrec.2024.01.006
10.1016/j.cviu.2022.103612
10.1016/j.knosys.2023.110480
10.1016/j.cviu.2023.103725
10.3390/app122211628
10.1109/ACCESS.2018.2875171
10.1007/s00521-019-04271-0
10.1109/LSP.2021.3134171
ContentType Journal Article
Copyright 2025 Elsevier Inc.
Copyright_xml – notice: 2025 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.dsp.2025.105312
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_dsp_2025_105312
S1051200425003343
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29G
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABDPE
ABFNM
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFS
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADFGL
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
CAG
COF
CS3
DM4
DU5
EBS
EFBJH
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG5
LG9
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SSH
SST
SSV
SSZ
T5K
WUQ
XPP
ZMT
ZU3
~G-
9DU
AAYXX
ACLOT
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c251t-c946ed5e2be2241eda6b8d5c39fb7e02e136cdfea2edf5536360a740fe06973c3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001499551800007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1051-2004
IngestDate Sat Nov 29 06:55:15 EST 2025
Sat Jul 05 17:10:59 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Computer vision
Gradient prior
Image deraining
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c251t-c946ed5e2be2241eda6b8d5c39fb7e02e136cdfea2edf5536360a740fe06973c3
ORCID 0009-0000-2626-2998
0009-0009-7236-8721
ParticipantIDs crossref_primary_10_1016_j_dsp_2025_105312
elsevier_sciencedirect_doi_10_1016_j_dsp_2025_105312
PublicationCentury 2000
PublicationDate October 2025
2025-10-00
PublicationDateYYYYMMDD 2025-10-01
PublicationDate_xml – month: 10
  year: 2025
  text: October 2025
PublicationDecade 2020
PublicationTitle Digital signal processing
PublicationYear 2025
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Li, Wu, Lin, Liu, Zha (br0060) 2018
Fu, Huang, Ding, Liao, Paisley (br0050) 2017; 26
Liang, Anwar, Liu (br0350) 2022
Deng, Wei, Wang, Feng, Liang, Xie, Wang, Wang (br0340) 2020
Zhou, Deng, Pang (br0370) 2024; 178
Wang, Yang, Xu, Chen, Zhang, Lau (br0330) 2019
Du, Deng, Zheng, Dong, He (br0150) 2023; 230
Zhang, Li, Li, Wang, Zhong, Fu (br0260) 2018
Wang, Jiang, Qian, Yang, Li, Zhang, Wang, Tang (br0290) 2017
Luo, Huang, Ling, Lin, Zhou (br0250) 2023; 268
Shen, Zhao, Li, Zhang, Sun, Peng (br0080) 2023; 233
Sun, Ren, Li, Zhang, Liang, Cao (br0180) 2023
Kulkarni, Patil, Murala (br0170) 2021; 29
Luo, Ling (br0300) 2020; 32
Han, Wang, Pan, Shen (br0240) 2022
Huang, Xu, Ren, Yang, Wan (br0220) 2022; 12
Deng, Huang, Zhao, Jiang (br0210) 2018; 59
Zhu, Fu, Lischinski, Heng (br0190) 2017
Fu, Huang, Zeng, Huang, Ding, Paisley (br0320) 2017
Chang, Chen, Yu, Li, Chen, Yan (br0130) 2023
Ren, Zuo, Hu, Zhu, Meng (br0090) 2019
Sutskever, Vinyals, Le (br0270) 2014; 27
Ren, Tian, Han, Chan, Tang (br0160) 2017
Luo, Xu, Ji (br0030) 2015
Luo, Zhu, Ling, Wu (br0040) 2018; 6
Kang, Lin, Fu (br0010) 2011; 21
Zamir, Arora, Khan, Hayat, Khan, Yang, Shao (br0070) 2021
Zhang, Sindagi, Patel (br0390) 2019; 30
Jiang, Chen, Lin, Zhao (br0100) 2021; 202
Chen, Hsu (br0020) 2013
Zheng, Chen, Wang, Wang, Wang (br0110) 2023; 235
Wang, Gao (br0380) 2025; 5
Liu, Zhang, Zhang, Pan, Yao, Ni, Han (br0120) 2023; 227
Wei, Zhang, Wang, Xu, Yang, Yan, Wang (br0280) 2021; 30
Jiang, Wang, Yi, Chen, Huang, Luo, Ma, Jiang (br0230) 2020
Charbonnier, Blanc-Feraud, Aubert, Barlaud (br0310) 1994
Lin, Zhang, Luo, Ling (br0140) 2023; 5
Chang, Yan, Zhong (br0200) 2017
Zheng, Lu, Wu, Gupta (br0360) 2022
Kulkarni (10.1016/j.dsp.2025.105312_br0170) 2021; 29
Zhang (10.1016/j.dsp.2025.105312_br0390) 2019; 30
Wei (10.1016/j.dsp.2025.105312_br0280) 2021; 30
Luo (10.1016/j.dsp.2025.105312_br0040) 2018; 6
Fu (10.1016/j.dsp.2025.105312_br0320) 2017
Zhu (10.1016/j.dsp.2025.105312_br0190) 2017
Huang (10.1016/j.dsp.2025.105312_br0220) 2022; 12
Li (10.1016/j.dsp.2025.105312_br0060) 2018
Luo (10.1016/j.dsp.2025.105312_br0300) 2020; 32
Charbonnier (10.1016/j.dsp.2025.105312_br0310) 1994
Wang (10.1016/j.dsp.2025.105312_br0380) 2025; 5
Liang (10.1016/j.dsp.2025.105312_br0350) 2022
Ren (10.1016/j.dsp.2025.105312_br0160) 2017
Jiang (10.1016/j.dsp.2025.105312_br0230) 2020
Ren (10.1016/j.dsp.2025.105312_br0090) 2019
Zhou (10.1016/j.dsp.2025.105312_br0370) 2024; 178
Chang (10.1016/j.dsp.2025.105312_br0130) 2023
Han (10.1016/j.dsp.2025.105312_br0240) 2022
Kang (10.1016/j.dsp.2025.105312_br0010) 2011; 21
Du (10.1016/j.dsp.2025.105312_br0150) 2023; 230
Sun (10.1016/j.dsp.2025.105312_br0180) 2023
Zamir (10.1016/j.dsp.2025.105312_br0070) 2021
Chen (10.1016/j.dsp.2025.105312_br0020) 2013
Lin (10.1016/j.dsp.2025.105312_br0140) 2023; 5
Shen (10.1016/j.dsp.2025.105312_br0080) 2023; 233
Zhang (10.1016/j.dsp.2025.105312_br0260) 2018
Sutskever (10.1016/j.dsp.2025.105312_br0270) 2014; 27
Zheng (10.1016/j.dsp.2025.105312_br0110) 2023; 235
Deng (10.1016/j.dsp.2025.105312_br0210) 2018; 59
Wang (10.1016/j.dsp.2025.105312_br0290) 2017
Fu (10.1016/j.dsp.2025.105312_br0050) 2017; 26
Luo (10.1016/j.dsp.2025.105312_br0250) 2023; 268
Chang (10.1016/j.dsp.2025.105312_br0200) 2017
Luo (10.1016/j.dsp.2025.105312_br0030) 2015
Liu (10.1016/j.dsp.2025.105312_br0120) 2023; 227
Wang (10.1016/j.dsp.2025.105312_br0330) 2019
Zheng (10.1016/j.dsp.2025.105312_br0360) 2022
Jiang (10.1016/j.dsp.2025.105312_br0100) 2021; 202
Deng (10.1016/j.dsp.2025.105312_br0340) 2020
References_xml – start-page: 14560
  year: 2020
  end-page: 14569
  ident: br0340
  article-title: Detail-recovery image deraining via context aggregation networks
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 30
  start-page: 4788
  year: 2021
  end-page: 4801
  ident: br0280
  article-title: DerainCycleGAN: rain attentive cyclegan for single image deraining and rainmaking
  publication-title: IEEE Trans. Image Process.
– volume: 202
  year: 2021
  ident: br0100
  article-title: Single image rain removal via multi-module deep grid network
  publication-title: Comput. Vis. Image Underst.
– start-page: 168
  year: 1994
  end-page: 172
  ident: br0310
  article-title: Two deterministic half-quadratic regularization algorithms for computed imaging
  publication-title: Proceedings of 1st International Conference on Image Processing, vol. 2
– volume: 227
  year: 2023
  ident: br0120
  article-title: Recurrent context-aware multi-stage network for single image deraining
  publication-title: Comput. Vis. Image Underst.
– start-page: 589
  year: 2022
  end-page: 598
  ident: br0350
  article-title: DRT: a lightweight single image deraining recursive transformer
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 21
  start-page: 1742
  year: 2011
  end-page: 1755
  ident: br0010
  article-title: Automatic single-image-based rain streaks removal via image decomposition
  publication-title: IEEE Trans. Image Process.
– start-page: 1968
  year: 2013
  end-page: 1975
  ident: br0020
  article-title: A generalized low-rank appearance model for spatio-temporally correlated rain streaks
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 235
  year: 2023
  ident: br0110
  article-title: Memory-efficient multi-scale residual dense network for single image rain removal
  publication-title: Comput. Vis. Image Underst.
– year: 2023
  ident: br0130
  article-title: Direction and residual awareness curriculum learning network for rain streaks removal
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 59
  start-page: 662
  year: 2018
  end-page: 679
  ident: br0210
  article-title: A directional global sparse model for single image rain removal
  publication-title: Appl. Math. Model.
– start-page: 12270
  year: 2019
  end-page: 12279
  ident: br0330
  article-title: Spatial attentive single-image deraining with a high quality real rain dataset
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 52
  year: 2022
  end-page: 62
  ident: br0360
  article-title: SAPNet: segmentation-aware progressive network for perceptual contrastive deraining
  publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision
– volume: 233
  year: 2023
  ident: br0080
  article-title: Local to non-local: multi-scale progressive attention network for image restoration
  publication-title: Comput. Vis. Image Underst.
– volume: 29
  start-page: 229
  year: 2021
  end-page: 233
  ident: br0170
  article-title: Progressive subtractive recurrent lightweight network for video deraining
  publication-title: IEEE Signal Process. Lett.
– start-page: 254
  year: 2018
  end-page: 269
  ident: br0060
  article-title: Recurrent squeeze-and-excitation context aggregation net for single image deraining
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– start-page: 3937
  year: 2019
  end-page: 3946
  ident: br0090
  article-title: Progressive image deraining networks: a better and simpler baseline
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– volume: 30
  start-page: 3943
  year: 2019
  end-page: 3956
  ident: br0390
  article-title: Image de-raining using a conditional generative adversarial network
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 3156
  year: 2017
  end-page: 3164
  ident: br0290
  article-title: Residual attention network for image classification
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 2526
  year: 2017
  end-page: 2534
  ident: br0190
  article-title: Joint bi-layer optimization for single-image rain streak removal
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 5
  start-page: 48
  year: 2025
  end-page: 60
  ident: br0380
  article-title: DECTNet: a detail enhanced CNN-transformer network for single-image deraining
  publication-title: Cogn. Robot.
– start-page: 14821
  year: 2021
  end-page: 14831
  ident: br0070
  article-title: Multi-stage progressive image restoration
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 8346
  year: 2020
  end-page: 8355
  ident: br0230
  article-title: Multi-scale progressive fusion network for single image deraining
  publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
– start-page: 3855
  year: 2017
  end-page: 3863
  ident: br0320
  article-title: Removing rain from single images via a deep detail network
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 1726
  year: 2017
  end-page: 1734
  ident: br0200
  article-title: Transformed low-rank model for line pattern noise removal
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– start-page: 4823
  year: 2022
  end-page: 4828
  ident: br0240
  article-title: MSDR-Net: multi-scale detail-recovery network for single image deraining
  publication-title: 2022 China Automation Congress (CAC)
– volume: 26
  start-page: 2944
  year: 2017
  end-page: 2956
  ident: br0050
  article-title: Clearing the skies: a deep network architecture for single-image rain removal
  publication-title: IEEE Trans. Image Process.
– start-page: 3397
  year: 2015
  end-page: 3405
  ident: br0030
  article-title: Removing rain from a single image via discriminative sparse coding
  publication-title: Proceedings of the IEEE International Conference on Computer Vision
– volume: 178
  start-page: 153
  year: 2024
  end-page: 159
  ident: br0370
  article-title: Recovering a clean background: a parallel deep network architecture for single-image deraining
  publication-title: Pattern Recognit. Lett.
– volume: 12
  year: 2022
  ident: br0220
  article-title: Rain removal of single image based on directional gradient priors
  publication-title: Appl. Sci.
– year: 2023
  ident: br0180
  article-title: Event-aware video deraining via multi-patch progressive learning
  publication-title: IEEE Trans. Image Process.
– volume: 5
  start-page: 11
  year: 2023
  end-page: 23
  ident: br0140
  article-title: Unrolling rain-guided detail recovery network for single image deraining
  publication-title: Virtual Real. Intell. Hardw.
– start-page: 4210
  year: 2017
  end-page: 4219
  ident: br0160
  article-title: Video desnowing and deraining based on matrix decomposition
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 27
  year: 2014
  ident: br0270
  article-title: Sequence to sequence learning with neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 32
  start-page: 7503
  year: 2020
  end-page: 7514
  ident: br0300
  article-title: Single-image de-raining using low-rank matrix approximation
  publication-title: Neural Comput. Appl.
– volume: 230
  year: 2023
  ident: br0150
  article-title: DSDNet: toward single image deraining with self-paced curricular dual stimulations
  publication-title: Comput. Vis. Image Underst.
– volume: 268
  year: 2023
  ident: br0250
  article-title: Local and global knowledge distillation with direction-enhanced contrastive learning for single-image deraining
  publication-title: Knowl.-Based Syst.
– volume: 6
  start-page: 60069
  year: 2018
  end-page: 60078
  ident: br0040
  article-title: Fast removal of rain streaks from a single image via a shape prior
  publication-title: IEEE Access
– start-page: 286
  year: 2018
  end-page: 301
  ident: br0260
  article-title: Image super-resolution using very deep residual channel attention networks
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– start-page: 12270
  year: 2019
  ident: 10.1016/j.dsp.2025.105312_br0330
  article-title: Spatial attentive single-image deraining with a high quality real rain dataset
– start-page: 168
  year: 1994
  ident: 10.1016/j.dsp.2025.105312_br0310
  article-title: Two deterministic half-quadratic regularization algorithms for computed imaging
– volume: 202
  year: 2021
  ident: 10.1016/j.dsp.2025.105312_br0100
  article-title: Single image rain removal via multi-module deep grid network
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2020.103106
– start-page: 3397
  year: 2015
  ident: 10.1016/j.dsp.2025.105312_br0030
  article-title: Removing rain from a single image via discriminative sparse coding
– start-page: 3855
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0320
  article-title: Removing rain from single images via a deep detail network
– start-page: 52
  year: 2022
  ident: 10.1016/j.dsp.2025.105312_br0360
  article-title: SAPNet: segmentation-aware progressive network for perceptual contrastive deraining
– start-page: 4210
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0160
  article-title: Video desnowing and deraining based on matrix decomposition
– start-page: 8346
  year: 2020
  ident: 10.1016/j.dsp.2025.105312_br0230
  article-title: Multi-scale progressive fusion network for single image deraining
– volume: 30
  start-page: 4788
  year: 2021
  ident: 10.1016/j.dsp.2025.105312_br0280
  article-title: DerainCycleGAN: rain attentive cyclegan for single image deraining and rainmaking
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3074804
– volume: 21
  start-page: 1742
  year: 2011
  ident: 10.1016/j.dsp.2025.105312_br0010
  article-title: Automatic single-image-based rain streaks removal via image decomposition
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2011.2179057
– volume: 5
  start-page: 11
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0140
  article-title: Unrolling rain-guided detail recovery network for single image deraining
  publication-title: Virtual Real. Intell. Hardw.
  doi: 10.1016/j.vrih.2022.06.002
– volume: 30
  start-page: 3943
  year: 2019
  ident: 10.1016/j.dsp.2025.105312_br0390
  article-title: Image de-raining using a conditional generative adversarial network
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
  doi: 10.1109/TCSVT.2019.2920407
– volume: 235
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0110
  article-title: Memory-efficient multi-scale residual dense network for single image rain removal
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2023.103766
– volume: 5
  start-page: 48
  year: 2025
  ident: 10.1016/j.dsp.2025.105312_br0380
  article-title: DECTNet: a detail enhanced CNN-transformer network for single-image deraining
  publication-title: Cogn. Robot.
  doi: 10.1016/j.cogr.2024.12.002
– volume: 230
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0150
  article-title: DSDNet: toward single image deraining with self-paced curricular dual stimulations
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2023.103657
– volume: 27
  year: 2014
  ident: 10.1016/j.dsp.2025.105312_br0270
  article-title: Sequence to sequence learning with neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 3156
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0290
  article-title: Residual attention network for image classification
– start-page: 14821
  year: 2021
  ident: 10.1016/j.dsp.2025.105312_br0070
  article-title: Multi-stage progressive image restoration
– volume: 59
  start-page: 662
  year: 2018
  ident: 10.1016/j.dsp.2025.105312_br0210
  article-title: A directional global sparse model for single image rain removal
  publication-title: Appl. Math. Model.
  doi: 10.1016/j.apm.2018.03.001
– volume: 26
  start-page: 2944
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0050
  article-title: Clearing the skies: a deep network architecture for single-image rain removal
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2691802
– start-page: 3937
  year: 2019
  ident: 10.1016/j.dsp.2025.105312_br0090
  article-title: Progressive image deraining networks: a better and simpler baseline
– year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0180
  article-title: Event-aware video deraining via multi-patch progressive learning
  publication-title: IEEE Trans. Image Process.
– volume: 178
  start-page: 153
  year: 2024
  ident: 10.1016/j.dsp.2025.105312_br0370
  article-title: Recovering a clean background: a parallel deep network architecture for single-image deraining
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2024.01.006
– start-page: 1968
  year: 2013
  ident: 10.1016/j.dsp.2025.105312_br0020
  article-title: A generalized low-rank appearance model for spatio-temporally correlated rain streaks
– start-page: 254
  year: 2018
  ident: 10.1016/j.dsp.2025.105312_br0060
  article-title: Recurrent squeeze-and-excitation context aggregation net for single image deraining
– volume: 227
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0120
  article-title: Recurrent context-aware multi-stage network for single image deraining
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2022.103612
– volume: 268
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0250
  article-title: Local and global knowledge distillation with direction-enhanced contrastive learning for single-image deraining
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2023.110480
– volume: 233
  year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0080
  article-title: Local to non-local: multi-scale progressive attention network for image restoration
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2023.103725
– volume: 12
  year: 2022
  ident: 10.1016/j.dsp.2025.105312_br0220
  article-title: Rain removal of single image based on directional gradient priors
  publication-title: Appl. Sci.
  doi: 10.3390/app122211628
– start-page: 4823
  year: 2022
  ident: 10.1016/j.dsp.2025.105312_br0240
  article-title: MSDR-Net: multi-scale detail-recovery network for single image deraining
– volume: 6
  start-page: 60069
  year: 2018
  ident: 10.1016/j.dsp.2025.105312_br0040
  article-title: Fast removal of rain streaks from a single image via a shape prior
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2875171
– start-page: 2526
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0190
  article-title: Joint bi-layer optimization for single-image rain streak removal
– volume: 32
  start-page: 7503
  year: 2020
  ident: 10.1016/j.dsp.2025.105312_br0300
  article-title: Single-image de-raining using low-rank matrix approximation
  publication-title: Neural Comput. Appl.
  doi: 10.1007/s00521-019-04271-0
– volume: 29
  start-page: 229
  year: 2021
  ident: 10.1016/j.dsp.2025.105312_br0170
  article-title: Progressive subtractive recurrent lightweight network for video deraining
  publication-title: IEEE Signal Process. Lett.
  doi: 10.1109/LSP.2021.3134171
– start-page: 1726
  year: 2017
  ident: 10.1016/j.dsp.2025.105312_br0200
  article-title: Transformed low-rank model for line pattern noise removal
– start-page: 286
  year: 2018
  ident: 10.1016/j.dsp.2025.105312_br0260
  article-title: Image super-resolution using very deep residual channel attention networks
– year: 2023
  ident: 10.1016/j.dsp.2025.105312_br0130
  article-title: Direction and residual awareness curriculum learning network for rain streaks removal
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– start-page: 589
  year: 2022
  ident: 10.1016/j.dsp.2025.105312_br0350
  article-title: DRT: a lightweight single image deraining recursive transformer
– start-page: 14560
  year: 2020
  ident: 10.1016/j.dsp.2025.105312_br0340
  article-title: Detail-recovery image deraining via context aggregation networks
SSID ssj0007426
Score 2.407159
Snippet The issue of rain removal in images is challenging due to the diverse rain distributions and complex backgrounds. Although deraining capabilities have greatly...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 105312
SubjectTerms Computer vision
Gradient prior
Image deraining
Title RGPNet: Learning a detail-preserved progressive model for single image deraining based on gradient prior
URI https://dx.doi.org/10.1016/j.dsp.2025.105312
Volume 165
WOSCitedRecordID wos001499551800007&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 1051-2004
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0007426
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1NT9tAEF2loYf2UPVTQAvaQ0-NjBw76_VyQ4XSIhShikppL9baOwYj6qCQRPTfd2bXa0wEUjn0YkWreGx5nmdmx29mGPsIKRiFOAlEKXCDYoQJcqNQIUmaxqnUYVjY7vrHcjxOJxN10uv98bUwy0tZ1-nNjbr6r6rGNVQ2lc4-Qt2tUFzA36h0PKLa8fhPiv9-eDIGm_A79mkPPXBM0YBYr0RxNI6XRRTYJbhpOJZvSImDSxhUv4nJQz057fiIAbk6Q58VzmaWITbH06vprBvY7ldnNH5kQHwQKu5y9QfeLxLjZ2GTsj8X7ULVpKoPNTqnDjWombJyVLWY-3U-XVhgQSOvSVNEoiW8ecuKb7_TU9f0JqJjPIdkEKJ77bpLMVzsmGvqMRqJndv_3u2hveLbWsahJ7NdZCgiIxGZE_GErUVSqLTP1va-HUyOWjcuR3ZWX3vf_pO4JQeu3Mf9QU0nUDl9yV40Owy-55DxivWgfs2ed_pOvmHnDiO73COEa76KEN5BCLcI4YgQ7hDCLUJ4ixBuEcKnNfcI4RYhb9mPLwenn78GzciNoMBAdx4UapSAERDlQLEdGJ3kqRFFrMpcQhjBME4KU4KOwJRCxNRtTstRWEKYKBkX8TvWr6c1rDOOYQ5u7ZXUOh5SkiKPY6EllYVJmcsw3GCf_DPLrlxnlexBLW2wkX-qWRMaupAvQ4Q8fNrmY67xnj27Be4H1p_PFrDFnhbLeXU9227g8RewF4Oe
linkProvider Elsevier
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=RGPNet%3A+Learning+a+detail-preserved+progressive+model+for+single+image+deraining+based+on+gradient+prior&rft.jtitle=Digital+signal+processing&rft.au=Luo%2C+Yu&rft.au=Liang%2C+Gaoquan&rft.au=Ling%2C+Jie&rft.au=Zhou%2C+Teng&rft.date=2025-10-01&rft.issn=1051-2004&rft.volume=165&rft.spage=105312&rft_id=info:doi/10.1016%2Fj.dsp.2025.105312&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_dsp_2025_105312
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-2004&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-2004&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-2004&client=summon