From heavy rain removal to detail restoration: A faster and better network

The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural details. Despite the improvements observed in existing learning-based methods specialized for heavy rain removal, it is discerned that a significan...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 148; p. 110205
Main Authors: Wen, Yuanbo, Gao, Tao, Zhang, Jing, Zhang, Kaihao, Chen, Ting
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.04.2024
Subjects:
ISSN:0031-3203
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural details. Despite the improvements observed in existing learning-based methods specialized for heavy rain removal, it is discerned that a significant proportion of these methods tend to overlook the precise reconstruction of the intricate details. In this work, we introduce a simple dual-stage progressive enhancement network, denoted as DPENet, aiming to achieve effective deraining while preserving the structural accuracy of rain-free images. This approach comprises two key modules, a rain streaks removal network (R2Net) focusing on accurate rain removal, and a details reconstruction network (DRNet) designed to recover the textural details of rain-free images. Firstly, we introduce a dilated dense residual block (DDRB) within R2Net, enabling the aggregation of high-level and low-level features. Secondly, an enhanced residual pixel-wise attention block (ERPAB) is integrated into DRNet to facilitate the incorporation of contextual information. To further enhance the fidelity of our approach, we employ a comprehensive loss function that accentuates both the marginal and regional accuracy of rain-free images. Extensive experiments conducted on publicly available benchmarks demonstrates the noteworthy efficiency and effectiveness of our proposed DPENet. The source code and pre-trained models are currently available at https://github.com/chdwyb/DPENet. •Dual-stage deraining network performs better than the single-stage network.•Multi-level feature fusion is significant for rain streaks removal.•Contextual information aggregation facilitates textural details reconstruction.
AbstractList The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural details. Despite the improvements observed in existing learning-based methods specialized for heavy rain removal, it is discerned that a significant proportion of these methods tend to overlook the precise reconstruction of the intricate details. In this work, we introduce a simple dual-stage progressive enhancement network, denoted as DPENet, aiming to achieve effective deraining while preserving the structural accuracy of rain-free images. This approach comprises two key modules, a rain streaks removal network (R2Net) focusing on accurate rain removal, and a details reconstruction network (DRNet) designed to recover the textural details of rain-free images. Firstly, we introduce a dilated dense residual block (DDRB) within R2Net, enabling the aggregation of high-level and low-level features. Secondly, an enhanced residual pixel-wise attention block (ERPAB) is integrated into DRNet to facilitate the incorporation of contextual information. To further enhance the fidelity of our approach, we employ a comprehensive loss function that accentuates both the marginal and regional accuracy of rain-free images. Extensive experiments conducted on publicly available benchmarks demonstrates the noteworthy efficiency and effectiveness of our proposed DPENet. The source code and pre-trained models are currently available at https://github.com/chdwyb/DPENet. •Dual-stage deraining network performs better than the single-stage network.•Multi-level feature fusion is significant for rain streaks removal.•Contextual information aggregation facilitates textural details reconstruction.
ArticleNumber 110205
Author Zhang, Jing
Wen, Yuanbo
Chen, Ting
Zhang, Kaihao
Gao, Tao
Author_xml – sequence: 1
  givenname: Yuanbo
  orcidid: 0000-0001-7599-5645
  surname: Wen
  fullname: Wen, Yuanbo
  organization: School of Information Engineering, Chang’an University, Xi’an 710064, China
– sequence: 2
  givenname: Tao
  orcidid: 0000-0002-5750-7449
  surname: Gao
  fullname: Gao, Tao
  email: tgaochd@126.com
  organization: School of Information Engineering, Chang’an University, Xi’an 710064, China
– sequence: 3
  givenname: Jing
  orcidid: 0000-0002-8516-0913
  surname: Zhang
  fullname: Zhang, Jing
  organization: School of Computing, Australian National University, Canberra, ACT 2600, Australia
– sequence: 4
  givenname: Kaihao
  orcidid: 0000-0002-4317-660X
  surname: Zhang
  fullname: Zhang, Kaihao
  organization: School of Computing, Australian National University, Canberra, ACT 2600, Australia
– sequence: 5
  givenname: Ting
  orcidid: 0000-0002-8134-6913
  surname: Chen
  fullname: Chen, Ting
  organization: School of Information Engineering, Chang’an University, Xi’an 710064, China
BookMark eNqFkMtOwzAQRb0oEi3wByz8Awl-po8FUlVRHqrEBtaWM56ASxpXtlXUvyclrFjAakYjnau5Z0JGXeiQkGvOSs54dbMt9zZDeCsFE7LknAmmR2TMmOSFFEyek0lKW8b4lCsxJk_rGHb0He3hSKP1HY24Cwfb0hyow2x9219SDtFmH7oFXdLGpoyR2s7RGvNp7TB_hvhxSc4a2ya8-pkX5HV997J6KDbP94-r5aYAyapcVBYQlFZSN8IpVWtd1aAl43M5rYSACmopFMyk082sargGgY5LreaONcBRXpDFkAsxpBSxMeDz93u5b9AazszJhNmawYQ5mTCDiR5Wv-B99Dsbj_9htwOGfbGDx2gSeOwAnY8I2bjg_w74Ai6afic
CitedBy_id crossref_primary_10_1109_ACCESS_2024_3523419
crossref_primary_10_1109_TMM_2025_3535316
crossref_primary_10_1016_j_patcog_2024_110840
crossref_primary_10_1016_j_patcog_2024_111313
crossref_primary_10_1016_j_patcog_2025_111643
crossref_primary_10_1007_s40747_024_01711_w
crossref_primary_10_1016_j_patcog_2024_110743
crossref_primary_10_1016_j_neucom_2025_131089
crossref_primary_10_1016_j_patcog_2024_111057
crossref_primary_10_1063_5_0228247
crossref_primary_10_1007_s10994_025_06854_6
crossref_primary_10_1016_j_asoc_2025_113506
crossref_primary_10_1016_j_neunet_2024_106428
crossref_primary_10_1016_j_neunet_2025_107739
crossref_primary_10_1016_j_eswa_2025_128511
crossref_primary_10_1016_j_knosys_2025_114086
crossref_primary_10_1016_j_patcog_2025_112075
Cites_doi 10.1109/TGRS.2023.3325927
10.1145/3503161.3547760
10.1109/TNNLS.2019.2926481
10.1109/TPAMI.2010.161
10.1145/3503161.3547932
10.1109/CVPR52729.2023.00571
10.1145/3503161.3548241
10.1109/TIP.2021.3102504
10.1007/978-3-030-01234-2_16
10.1109/TPAMI.2019.2895793
10.1016/j.patcog.2022.109294
10.1109/CVPR.2017.243
10.1109/TCSVT.2019.2920407
10.1145/3343031.3351149
10.1109/TIP.2017.2691802
10.1109/TIP.2021.3074804
ContentType Journal Article
Copyright 2023 Elsevier Ltd
Copyright_xml – notice: 2023 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2023.110205
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_patcog_2023_110205
S0031320323009020
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 52172379; 62001058; U1864204
  funderid: http://dx.doi.org/10.13039/501100001809
– fundername: National Key R and D Program of China
  grantid: 2019YFE0108300
  funderid: http://dx.doi.org/10.13039/501100012166
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABDPE
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABWVN
ABXDB
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACRPL
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADNMO
ADTZH
AEBSH
AECPX
AEFWE
AEIPS
AEKER
AENEX
AFJKZ
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SSH
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AAYXX
ACLOT
ACVFH
ADCNI
AEUPX
AFPUW
AIGII
AIIUN
AKBMS
AKYEP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c306t-6acec45435f2d44b556bc5301937622c6cb324c83d5f86f15c2ed13549d0fc1e3
ISICitedReferencesCount 20
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001147362400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 07:28:29 EST 2025
Tue Nov 18 21:51:59 EST 2025
Fri May 16 00:30:49 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Dual-stage network
Dilated convolution
Single image deraining
Pixel-wise attention
Detail reconstruction
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-6acec45435f2d44b556bc5301937622c6cb324c83d5f86f15c2ed13549d0fc1e3
ORCID 0000-0002-5750-7449
0000-0002-8134-6913
0000-0001-7599-5645
0000-0002-4317-660X
0000-0002-8516-0913
ParticipantIDs crossref_citationtrail_10_1016_j_patcog_2023_110205
crossref_primary_10_1016_j_patcog_2023_110205
elsevier_sciencedirect_doi_10_1016_j_patcog_2023_110205
PublicationCentury 2000
PublicationDate April 2024
2024-04-00
PublicationDateYYYYMMDD 2024-04-01
PublicationDate_xml – month: 04
  year: 2024
  text: April 2024
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References X. Chen, H. Li, M. Li, J. Pan, Learning A Sparse Transformer Network for Effective Image Deraining, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 5896–5905.
Y. Li, Y. Zhang, R. Timofte, L. Van Gool, L. Yu, Y. Li, X. Li, T. Jiang, Q. Wu, M. Han, et al., NTIRE 2023 challenge on efficient super-resolution: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1921–1959.
Wei, Zhang, Wang, Xu, Yang, Yan, Wang (b26) 2021; 30
Fu, Liang, Huang, Ding, Paisley (b12) 2019; 31
Yang, Tan, Feng, Guo, Yan, Liu (b29) 2019; 42
X. Li, J. Wu, Z. Lin, H. Liu, H. Zha, Recurrent squeeze-and-excitation context aggregation net for single image deraining, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 254–269.
Wang, Chen, Yuan, Liu, Huang, Hou, Cottrell (b20) 2018
Zhang, Sindagi, Patel (b34) 2019; 30
Pan, Yang, Yang, Wang, Tan (b33) 2021
Ren, Zuo, Hu, Zhu, Meng (b11) 2019
Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b32) 2014
Wen, Gao, Li, Zhang, Chen (b9) 2023
Yasarla, Patel (b14) 2019
Y. Zhang, K. Zhang, Z. Chen, Y. Li, R. Timofte, J. Zhang, K. Zhang, R. Peng, Y. Ma, L. Jia, et al., NTIRE 2023 challenge on image super-resolution (x4): Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1864–1883.
Matsumoto, Sakaue, Sato (b31) 2020
Gao, Wen, Zhang, Zhang, Chen, Liu, Luo (b2) 2023
Jiang, Wang, Yi, Chen, Huang, Luo, Ma, Jiang (b17) 2020
Yang, Tan, Feng, Liu, Guo, Yan (b22) 2017
Hsu, Chang (b16) 2023; 137
Zhang, Patel (b25) 2018
Ma, Liang (b30) 2016
Y. Yang, H. Lu, Single image deraining via recurrent hierarchy enhancement network, in: Proceedings of the 27th ACM International Conference on Multimedia, 2019, pp. 1814–1822.
Zhang, Luo, Ren, Wang, Zhao, Ma, Li (b6) 2020
Fu, Huang, Ding, Liao, Paisley (b10) 2017; 26
Arbelaez, Maire, Fowlkes, Malik (b37) 2010; 33
Y. Wei, Z. Zhang, M. Xu, R. Hong, J. Fan, S. Yan, Robust attention deraining network for synchronous rain streaks and raindrops removal, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6464–6472.
Zamir, Arora, Khan, Hayat, Khan, Yang, Shao (b23) 2021
Zhang, Wei, Zhang, Yang, Yan, Wang (b5) 2023
Schaefer, Stich (b38) 2003
Wen, Gao, Zhang, Li, Chen (b4) 2023
Wei, Meng, Zhao, Xu, Wu (b18) 2019
Y. Wei, Z. Zhang, H. Zheng, R. Hong, Y. Yang, M. Wang, Sginet: Toward sufficient interaction between single image deraining and semantic segmentation, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6202–6210.
Deng, Wei, Wang, Feng, Liang, Xie, Wang, Wang (b13) 2020
Li, Cheong, Tan (b28) 2019
He, Zhang, Ren, Sun (b35) 2016
Y. Li, Y. Zhang, R. Timofte, L. Van Gool, Z. Tu, K. Du, H. Wang, H. Chen, W. Li, X. Wang, et al., NTIRE 2023 challenge on image denoising: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1904–1920.
G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
Jiang, Wang, Yi, Chen, Wang, Wang, Jiang, Lin (b19) 2021; 30
L. Wang, Y. Guo, Y. Wang, J. Li, S. Gu, R. Timofte, M. Cheng, H. Ma, Q. Ma, X. Sun, et al., NTIRE 2023 challenge on stereo image super-resolution: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1346–1372.
K. Jiang, Z. Wang, C. Chen, Z. Wang, L. Cui, C.-W. Lin, Magic ELF: Image Deraining Meets Association Learning and Transformer, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 827–836.
10.1016/j.patcog.2023.110205_b27
Hsu (10.1016/j.patcog.2023.110205_b16) 2023; 137
10.1016/j.patcog.2023.110205_b1
He (10.1016/j.patcog.2023.110205_b35) 2016
Jiang (10.1016/j.patcog.2023.110205_b17) 2020
10.1016/j.patcog.2023.110205_b21
Pan (10.1016/j.patcog.2023.110205_b33) 2021
Jiang (10.1016/j.patcog.2023.110205_b19) 2021; 30
Yasarla (10.1016/j.patcog.2023.110205_b14) 2019
10.1016/j.patcog.2023.110205_b24
Gao (10.1016/j.patcog.2023.110205_b2) 2023
Zamir (10.1016/j.patcog.2023.110205_b23) 2021
Fu (10.1016/j.patcog.2023.110205_b12) 2019; 31
Ma (10.1016/j.patcog.2023.110205_b30) 2016
Goodfellow (10.1016/j.patcog.2023.110205_b32) 2014
Fu (10.1016/j.patcog.2023.110205_b10) 2017; 26
Wen (10.1016/j.patcog.2023.110205_b4) 2023
10.1016/j.patcog.2023.110205_b3
Li (10.1016/j.patcog.2023.110205_b28) 2019
Zhang (10.1016/j.patcog.2023.110205_b6) 2020
Wei (10.1016/j.patcog.2023.110205_b18) 2019
10.1016/j.patcog.2023.110205_b7
10.1016/j.patcog.2023.110205_b8
Ren (10.1016/j.patcog.2023.110205_b11) 2019
Yang (10.1016/j.patcog.2023.110205_b22) 2017
Zhang (10.1016/j.patcog.2023.110205_b25) 2018
10.1016/j.patcog.2023.110205_b39
Schaefer (10.1016/j.patcog.2023.110205_b38) 2003
Arbelaez (10.1016/j.patcog.2023.110205_b37) 2010; 33
Matsumoto (10.1016/j.patcog.2023.110205_b31) 2020
Zhang (10.1016/j.patcog.2023.110205_b34) 2019; 30
Wen (10.1016/j.patcog.2023.110205_b9) 2023
10.1016/j.patcog.2023.110205_b36
10.1016/j.patcog.2023.110205_b15
Zhang (10.1016/j.patcog.2023.110205_b5) 2023
Wei (10.1016/j.patcog.2023.110205_b26) 2021; 30
Yang (10.1016/j.patcog.2023.110205_b29) 2019; 42
10.1016/j.patcog.2023.110205_b40
Deng (10.1016/j.patcog.2023.110205_b13) 2020
Wang (10.1016/j.patcog.2023.110205_b20) 2018
References_xml – start-page: 14560
  year: 2020
  end-page: 14569
  ident: b13
  article-title: Detail-recovery image deraining via context aggregation networks
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 472
  year: 2003
  end-page: 480
  ident: b38
  article-title: UCID: An uncompressed color image database
  publication-title: Storage and Retrieval Methods and Applications for Multimedia 2004, Vol. 5307
– start-page: 1451
  year: 2018
  end-page: 1460
  ident: b20
  article-title: Understanding convolution for semantic segmentation
  publication-title: IEEE Winter Conference on Applications of Computer Vision
– volume: 33
  start-page: 898
  year: 2010
  end-page: 916
  ident: b37
  article-title: Contour detection and hierarchical image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– start-page: 8346
  year: 2020
  end-page: 8355
  ident: b17
  article-title: Multi-scale progressive fusion network for single image deraining
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– volume: 30
  start-page: 3943
  year: 2019
  end-page: 3956
  ident: b34
  article-title: Image de-raining using a conditional generative adversarial network
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– reference: X. Li, J. Wu, Z. Lin, H. Liu, H. Zha, Recurrent squeeze-and-excitation context aggregation net for single image deraining, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 254–269.
– reference: Y. Wei, Z. Zhang, M. Xu, R. Hong, J. Fan, S. Yan, Robust attention deraining network for synchronous rain streaks and raindrops removal, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6464–6472.
– start-page: 1633
  year: 2019
  end-page: 1642
  ident: b28
  article-title: Heavy rain image restoration: Integrating physics model and conditional adversarial learning
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 695
  year: 2018
  end-page: 704
  ident: b25
  article-title: Density-aware single image de-raining using a multi-stream dense network
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– volume: 30
  start-page: 7404
  year: 2021
  end-page: 7418
  ident: b19
  article-title: Rain-free and residue hand-in-hand: A progressive coupled network for real-time image deraining
  publication-title: IEEE Trans. Image Process.
– start-page: 128
  year: 2020
  end-page: 136
  ident: b31
  article-title: Recovering raindrop removal images under heavy rain.
  publication-title: VISIGRAPP (4: VISAPP)
– year: 2023
  ident: b9
  article-title: Multi-dimension queried and interacting network for stereo image deraining
  publication-title: arXiv preprint arXiv:2309.10319
– reference: Y. Zhang, K. Zhang, Z. Chen, Y. Li, R. Timofte, J. Zhang, K. Zhang, R. Peng, Y. Ma, L. Jia, et al., NTIRE 2023 challenge on image super-resolution (x4): Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1864–1883.
– volume: 30
  start-page: 4788
  year: 2021
  end-page: 4801
  ident: b26
  article-title: DerainCycleGAN: Rain attentive cyclegan for single image deraining and rainmaking
  publication-title: IEEE Trans. Image Process.
– year: 2023
  ident: b4
  article-title: Encoder-free multi-axis physics-aware fusion network for remote sensing image dehazing
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
– reference: K. Jiang, Z. Wang, C. Chen, Z. Wang, L. Cui, C.-W. Lin, Magic ELF: Image Deraining Meets Association Learning and Transformer, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 827–836.
– start-page: 2672
  year: 2014
  end-page: 2680
  ident: b32
  article-title: Generative adversarial nets
  publication-title: Conference on Neural Information Processing Systems, Vol. 27
– volume: 26
  start-page: 2944
  year: 2017
  end-page: 2956
  ident: b10
  article-title: Clearing the skies: A deep network architecture for single-image rain removal
  publication-title: IEEE Trans. Image Process.
– reference: Y. Li, Y. Zhang, R. Timofte, L. Van Gool, L. Yu, Y. Li, X. Li, T. Jiang, Q. Wu, M. Han, et al., NTIRE 2023 challenge on efficient super-resolution: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1921–1959.
– start-page: 14821
  year: 2021
  end-page: 14831
  ident: b23
  article-title: Multi-stage progressive image restoration
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 71
  year: 2020
  end-page: 89
  ident: b6
  article-title: Beyond monocular deraining: Stereo image deraining via semantic understanding
  publication-title: European Conference on Computer Vision
– volume: 137
  year: 2023
  ident: b16
  article-title: Recurrent wavelet structure-preserving residual network for single image deraining
  publication-title: Pattern Recognit.
– start-page: 770
  year: 2016
  end-page: 778
  ident: b35
  article-title: Deep residual learning for image recognition
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– year: 2023
  ident: b5
  article-title: Data-driven single image deraining: A comprehensive review and new perspectives
  publication-title: Pattern Recognit.
– reference: X. Chen, H. Li, M. Li, J. Pan, Learning A Sparse Transformer Network for Effective Image Deraining, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 5896–5905.
– start-page: 1357
  year: 2017
  end-page: 1366
  ident: b22
  article-title: Deep joint rain detection and removal from a single image
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– start-page: 3937
  year: 2019
  end-page: 3946
  ident: b11
  article-title: Progressive image deraining networks: A better and simpler baseline
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– reference: Y. Yang, H. Lu, Single image deraining via recurrent hierarchy enhancement network, in: Proceedings of the 27th ACM International Conference on Multimedia, 2019, pp. 1814–1822.
– reference: Y. Li, Y. Zhang, R. Timofte, L. Van Gool, Z. Tu, K. Du, H. Wang, H. Chen, W. Li, X. Wang, et al., NTIRE 2023 challenge on image denoising: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1904–1920.
– year: 2023
  ident: b2
  article-title: Frequency-oriented efficient transformer for all-in-one weather-degraded image restoration
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 3877
  year: 2019
  end-page: 3886
  ident: b18
  article-title: Semi-supervised transfer learning for image rain removal
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– reference: L. Wang, Y. Guo, Y. Wang, J. Li, S. Gu, R. Timofte, M. Cheng, H. Ma, Q. Ma, X. Sun, et al., NTIRE 2023 challenge on stereo image super-resolution: Methods and results, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1346–1372.
– start-page: 8405
  year: 2019
  end-page: 8414
  ident: b14
  article-title: Uncertainty guided multi-scale residual learning-using a cycle spinning cnn for single image de-raining
  publication-title: IEEE Conference on Computer Vision and Pattern Recognition
– reference: G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
– volume: 42
  start-page: 1377
  year: 2019
  end-page: 1393
  ident: b29
  article-title: Joint rain detection and removal from a single image with contextualized deep networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: Y. Wei, Z. Zhang, H. Zheng, R. Hong, Y. Yang, M. Wang, Sginet: Toward sufficient interaction between single image deraining and semantic segmentation, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6202–6210.
– volume: 31
  start-page: 1794
  year: 2019
  end-page: 1807
  ident: b12
  article-title: Lightweight pyramid networks for image deraining
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– start-page: 657
  year: 2016
  end-page: 667
  ident: b30
  article-title: A rain detection and removal algorithm based on rainy intensity for videos in heavy rainy scene
  publication-title: International Conference on Oriental Thinking and Fuzzy Logic
– year: 2021
  ident: b33
  article-title: Two-stage fusion model for heavy rain removal on single image
  publication-title: Journal of Physics: Conference Series, Vol. 2035
– ident: 10.1016/j.patcog.2023.110205_b27
– year: 2023
  ident: 10.1016/j.patcog.2023.110205_b5
  article-title: Data-driven single image deraining: A comprehensive review and new perspectives
  publication-title: Pattern Recognit.
– year: 2021
  ident: 10.1016/j.patcog.2023.110205_b33
  article-title: Two-stage fusion model for heavy rain removal on single image
– start-page: 3877
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b18
  article-title: Semi-supervised transfer learning for image rain removal
– year: 2023
  ident: 10.1016/j.patcog.2023.110205_b4
  article-title: Encoder-free multi-axis physics-aware fusion network for remote sensing image dehazing
  publication-title: IEEE Transactions on Geoscience and Remote Sensing
  doi: 10.1109/TGRS.2023.3325927
– ident: 10.1016/j.patcog.2023.110205_b15
  doi: 10.1145/3503161.3547760
– volume: 31
  start-page: 1794
  issue: 6
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b12
  article-title: Lightweight pyramid networks for image deraining
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2019.2926481
– start-page: 695
  year: 2018
  ident: 10.1016/j.patcog.2023.110205_b25
  article-title: Density-aware single image de-raining using a multi-stream dense network
– start-page: 3937
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b11
  article-title: Progressive image deraining networks: A better and simpler baseline
– volume: 33
  start-page: 898
  issue: 5
  year: 2010
  ident: 10.1016/j.patcog.2023.110205_b37
  article-title: Contour detection and hierarchical image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2010.161
– start-page: 71
  year: 2020
  ident: 10.1016/j.patcog.2023.110205_b6
  article-title: Beyond monocular deraining: Stereo image deraining via semantic understanding
– ident: 10.1016/j.patcog.2023.110205_b40
  doi: 10.1145/3503161.3547932
– start-page: 657
  year: 2016
  ident: 10.1016/j.patcog.2023.110205_b30
  article-title: A rain detection and removal algorithm based on rainy intensity for videos in heavy rainy scene
– ident: 10.1016/j.patcog.2023.110205_b7
  doi: 10.1109/CVPR52729.2023.00571
– ident: 10.1016/j.patcog.2023.110205_b8
  doi: 10.1145/3503161.3548241
– start-page: 8405
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b14
  article-title: Uncertainty guided multi-scale residual learning-using a cycle spinning cnn for single image de-raining
– year: 2023
  ident: 10.1016/j.patcog.2023.110205_b9
  article-title: Multi-dimension queried and interacting network for stereo image deraining
  publication-title: arXiv preprint arXiv:2309.10319
– start-page: 14560
  year: 2020
  ident: 10.1016/j.patcog.2023.110205_b13
  article-title: Detail-recovery image deraining via context aggregation networks
– volume: 30
  start-page: 7404
  year: 2021
  ident: 10.1016/j.patcog.2023.110205_b19
  article-title: Rain-free and residue hand-in-hand: A progressive coupled network for real-time image deraining
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3102504
– start-page: 1357
  year: 2017
  ident: 10.1016/j.patcog.2023.110205_b22
  article-title: Deep joint rain detection and removal from a single image
– ident: 10.1016/j.patcog.2023.110205_b36
  doi: 10.1007/978-3-030-01234-2_16
– volume: 42
  start-page: 1377
  issue: 6
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b29
  article-title: Joint rain detection and removal from a single image with contextualized deep networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2019.2895793
– volume: 137
  year: 2023
  ident: 10.1016/j.patcog.2023.110205_b16
  article-title: Recurrent wavelet structure-preserving residual network for single image deraining
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2022.109294
– start-page: 128
  year: 2020
  ident: 10.1016/j.patcog.2023.110205_b31
  article-title: Recovering raindrop removal images under heavy rain.
– year: 2023
  ident: 10.1016/j.patcog.2023.110205_b2
  article-title: Frequency-oriented efficient transformer for all-in-one weather-degraded image restoration
  publication-title: IEEE Trans. Circuits Syst. Video Technol.
– start-page: 8346
  year: 2020
  ident: 10.1016/j.patcog.2023.110205_b17
  article-title: Multi-scale progressive fusion network for single image deraining
– ident: 10.1016/j.patcog.2023.110205_b21
  doi: 10.1109/CVPR.2017.243
– ident: 10.1016/j.patcog.2023.110205_b24
– start-page: 472
  year: 2003
  ident: 10.1016/j.patcog.2023.110205_b38
  article-title: UCID: An uncompressed color image database
– start-page: 1451
  year: 2018
  ident: 10.1016/j.patcog.2023.110205_b20
  article-title: Understanding convolution for semantic segmentation
– start-page: 2672
  year: 2014
  ident: 10.1016/j.patcog.2023.110205_b32
  article-title: Generative adversarial nets
– volume: 30
  start-page: 3943
  issue: 11
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b34
  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
– ident: 10.1016/j.patcog.2023.110205_b39
  doi: 10.1145/3343031.3351149
– ident: 10.1016/j.patcog.2023.110205_b1
– volume: 26
  start-page: 2944
  issue: 6
  year: 2017
  ident: 10.1016/j.patcog.2023.110205_b10
  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: 1633
  year: 2019
  ident: 10.1016/j.patcog.2023.110205_b28
  article-title: Heavy rain image restoration: Integrating physics model and conditional adversarial learning
– volume: 30
  start-page: 4788
  year: 2021
  ident: 10.1016/j.patcog.2023.110205_b26
  article-title: DerainCycleGAN: Rain attentive cyclegan for single image deraining and rainmaking
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3074804
– start-page: 770
  year: 2016
  ident: 10.1016/j.patcog.2023.110205_b35
  article-title: Deep residual learning for image recognition
– start-page: 14821
  year: 2021
  ident: 10.1016/j.patcog.2023.110205_b23
  article-title: Multi-stage progressive image restoration
– ident: 10.1016/j.patcog.2023.110205_b3
SSID ssj0017142
Score 2.5690422
Snippet The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 110205
SubjectTerms Detail reconstruction
Dilated convolution
Dual-stage network
Pixel-wise attention
Single image deraining
Title From heavy rain removal to detail restoration: A faster and better network
URI https://dx.doi.org/10.1016/j.patcog.2023.110205
Volume 148
WOSCitedRecordID wos001147362400001&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: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017142
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1La9wwEBbbTQ-9NH3S9IUOvRkFr2xJVm9LSGi2EALd0u3JyLLcJiT2st0s6b_v6GGtS0r6gF7MIix7mU8ezYy-mUHoDWW6brgUhBtRkVwqTlSTNqSodQ3uCngITLtmE-LkpFgs5OloFLP4NxeibYvra7n8r1DDGIBtU2f_Au74UBiA3wA6XAF2uP4R8Ec2YQRU7OZ7Yts_JCtz2W0spbxLPF80WbluMpHWMU0aZcsluHOEyqX3JK1nhw9N11NXidM-L1COtgf4n7zu-nyl2qqLjB7lorBzFUdicHrW75fDwffq7Gu4N0Qh6JC84kJjfXrMlovk1G02IRlNs5_Ura-seUN1-yjC-f4StqDuy75t625zFGjKtltVJBB-8DUn0ww8KMssTe-gHSqYLMZoZ3p8uJjFkyQxyX3F-PBX-vRJx_G7-a5fmycDk2P-AN0PvgKeeowfopFpH6Hdvg8HDmr5MZpZyLGDHFvIcYAcrzvsIccDyN_iKfaAYwAce8BxAPwJ-nh0OD94R0KPDKLB2VsTrrTROQOjt6F1nleM8Uoz0NpgdnJKNdcVmMy6yGrWFLyBL4-aepKxXNZpoycme4rGbdeaZwhrQyWXVOdGWDPeGnJUKrsFwKZYCLWHsl40pQ4F5G0fk4uyZwqel16gpRVo6QW6h0ictfQFVH5zv-ilXgYj0Bt3JSyUW2c-_-eZL9C97Zp-icbr1ZV5he7qzfrs2-p1WFE_ALNDgPw
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=From+heavy+rain+removal+to+detail+restoration%3A+A+faster+and+better+network&rft.jtitle=Pattern+recognition&rft.au=Wen%2C+Yuanbo&rft.au=Gao%2C+Tao&rft.au=Zhang%2C+Jing&rft.au=Zhang%2C+Kaihao&rft.date=2024-04-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.volume=148&rft_id=info:doi/10.1016%2Fj.patcog.2023.110205&rft.externalDocID=S0031320323009020
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon