Poisson2Poisson-Sparse: Unsupervised Poisson noise image denoising based on sparse modeling

In fields such as low-light photography, astronomical imaging, and low-dose computed tomography scanning, Poisson noise severely degrades image quality due to extremely low photon counts (averaging below one) and their Poisson-distributed statistical characteristics. A recent self-supervised Poisson...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Signal processing Jg. 230; S. 109870
Hauptverfasser: Xiao, Lingzhi, Wang, Shengbiao, Zhang, Jun, Wei, Jiuzhe, Yang, Shihua
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.05.2025
Schlagworte:
ISSN:0165-1684
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In fields such as low-light photography, astronomical imaging, and low-dose computed tomography scanning, Poisson noise severely degrades image quality due to extremely low photon counts (averaging below one) and their Poisson-distributed statistical characteristics. A recent self-supervised Poisson denoising method uses only a single noisy image to improve image quality. However, it struggles under high Poisson noise due to its denoising model based on Gaussian distribution and suffers from long inference times. To address these issues, we propose an unsupervised Poisson denoising method based on sparse representation. Specifically, we first establish a more accurate sparse representation model based on Poisson distribution to enhance denoising performance. Given the difficulty of solving this model directly, we develop an iterative optimization algorithm using convolutional sparse coding and the alternating direction method of multipliers. Inspired by the unfolding technique, we further reduce computational cost by unfolding the iterative process into a finite-cycle learning network. To overcome the reliance on paired datasets and accelerate inference times, we employ a Poisson loss function, a Neighbor2Neighbor training strategy, and incorporate total variation loss, which together enable unsupervised learning. Experimental results demonstrate that our proposed method significantly outperforms existing unsupervised Poisson denoising methods and achieves high computational efficiency. •The Poisson fidelity term surpasses the Gaussian term in low-light Poisson denoising.•Effectively unfold the alternating direction method of multipliers as a network.•Convolutional sparse coding serves as a byproduct of the denoising network.•The optimal unsupervised unfolding method for Poisson denoising in low light.•TV loss effectively suppresses artifacts in Poisson unsupervised denoising.
AbstractList In fields such as low-light photography, astronomical imaging, and low-dose computed tomography scanning, Poisson noise severely degrades image quality due to extremely low photon counts (averaging below one) and their Poisson-distributed statistical characteristics. A recent self-supervised Poisson denoising method uses only a single noisy image to improve image quality. However, it struggles under high Poisson noise due to its denoising model based on Gaussian distribution and suffers from long inference times. To address these issues, we propose an unsupervised Poisson denoising method based on sparse representation. Specifically, we first establish a more accurate sparse representation model based on Poisson distribution to enhance denoising performance. Given the difficulty of solving this model directly, we develop an iterative optimization algorithm using convolutional sparse coding and the alternating direction method of multipliers. Inspired by the unfolding technique, we further reduce computational cost by unfolding the iterative process into a finite-cycle learning network. To overcome the reliance on paired datasets and accelerate inference times, we employ a Poisson loss function, a Neighbor2Neighbor training strategy, and incorporate total variation loss, which together enable unsupervised learning. Experimental results demonstrate that our proposed method significantly outperforms existing unsupervised Poisson denoising methods and achieves high computational efficiency. •The Poisson fidelity term surpasses the Gaussian term in low-light Poisson denoising.•Effectively unfold the alternating direction method of multipliers as a network.•Convolutional sparse coding serves as a byproduct of the denoising network.•The optimal unsupervised unfolding method for Poisson denoising in low light.•TV loss effectively suppresses artifacts in Poisson unsupervised denoising.
ArticleNumber 109870
Author Wei, Jiuzhe
Wang, Shengbiao
Yang, Shihua
Xiao, Lingzhi
Zhang, Jun
Author_xml – sequence: 1
  givenname: Lingzhi
  orcidid: 0009-0007-0005-3611
  surname: Xiao
  fullname: Xiao, Lingzhi
  email: xiaolingzhi2000@njust.edu.cn
  organization: School of Mathematics and Statistics, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China
– sequence: 2
  givenname: Shengbiao
  surname: Wang
  fullname: Wang, Shengbiao
  organization: School of Mathematics and Statistics, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China
– sequence: 3
  givenname: Jun
  surname: Zhang
  fullname: Zhang, Jun
  email: phil_zj@njust.edu.cn
  organization: School of Mathematics and Statistics, Nanjing University of Science and Technology, Nanjing, 210094, Jiangsu, China
– sequence: 4
  givenname: Jiuzhe
  surname: Wei
  fullname: Wei, Jiuzhe
  organization: Beijing Institute of Space Mechanics and Electricity, Beijing, 100076, China
– sequence: 5
  givenname: Shihua
  surname: Yang
  fullname: Yang, Shihua
  organization: Beijing Institute of Space Mechanics and Electricity, Beijing, 100076, China
BookMark eNqFkE1LAzEQhnOoYKv-Aw_5A1snm_3sQZDiFxQUrCcPIU0mJaVNlmQt-O_Nuj150NPLzDvPMPPOyMR5h4RcM5gzYNXNbh7ttgt-nkNepFbb1DAh02SVGaua4pzMYtwBAOMVTMnHq7cxepefNHvrZIi4oO8ufnYYjjaipieTuqRI7UFukWocKuu2dCOHmWTHH5YevMZ9Mi7JmZH7iFcnvSDrh_v18ilbvTw-L-9WmeJQ9RnXea4NaNNyA3XeAChgOTCzMbxRdVE0pa4kB11jC5u2bhCqskE0rNSFYfyCFONaFXyMAY3oQjoxfAkGYshE7MSYiRgyEWMmCVv8wpTtZW-964O0-__g2xHG9NfRYhBRWXQKtQ2oeqG9_XvBNwcGhY4
CitedBy_id crossref_primary_10_1016_j_knosys_2025_114230
crossref_primary_10_3788_LOP250975
Cites_doi 10.1002/cpa.20042
10.1109/CVPRW.2019.00242
10.23919/ICCAS55662.2022.10003847
10.1109/TIP.2018.2859044
10.1109/CVPR.2015.7299163
10.1088/2399-6528/ac0eca
10.1109/ICIP.2010.5653394
10.2307/2332343
10.1109/TIP.2010.2056693
10.1109/ICIP49359.2023.10222230
10.1109/ICASSP.2018.8462313
10.1109/ICASSP43922.2022.9746870
10.1198/106186004X2697
10.3934/ipi.2021003
10.1109/TIP.2021.3090531
10.1109/TIP.2021.3087943
10.1109/TIP.2014.2362057
10.1007/s10851-013-0435-6
10.1109/TIP.2022.3176533
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.sigpro.2024.109870
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_sigpro_2024_109870
S0165168424004900
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXKI
AAXUO
AAYFN
ABBOA
ABDPE
ABFNM
ABFRF
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACRPL
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEFWE
AEIPS
AEKER
AENEX
AFJKZ
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG9
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TAE
TN5
WUQ
XPP
ZMT
~02
~G-
9DU
AATTM
AAYWO
AAYXX
ACLOT
ACVFH
ADCNI
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c306t-3d22df0df93f072800c01201fbf38c74485d6a30d7e90b978e0658eef15d4f13
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001420447600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0165-1684
IngestDate Sat Nov 29 08:18:23 EST 2025
Tue Nov 18 20:53:13 EST 2025
Sat Mar 01 15:45:28 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Unfolding
Poisson noise
Convolutional sparse coding
Unsupervised learning
Image denoising
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-3d22df0df93f072800c01201fbf38c74485d6a30d7e90b978e0658eef15d4f13
ORCID 0009-0007-0005-3611
ParticipantIDs crossref_primary_10_1016_j_sigpro_2024_109870
crossref_citationtrail_10_1016_j_sigpro_2024_109870
elsevier_sciencedirect_doi_10_1016_j_sigpro_2024_109870
PublicationCentury 2000
PublicationDate May 2025
2025-05-00
PublicationDateYYYYMMDD 2025-05-01
PublicationDate_xml – month: 05
  year: 2025
  text: May 2025
PublicationDecade 2020
PublicationTitle Signal processing
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Zhao, Wen, Ng, Li (b16) 2021; 15
Simon, Elad (b21) 2019; 32
Scetbon, Elad, Milanfar (b29) 2021; 30
Z. Zha, B. Wen, X. Yuan, J. Zhou, C. Zhu, Simultaneous nonlocal low-rank and deep priors for Poisson denoising, in: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2022, pp. 2320–2324.
Brinkmann, Brinker, Rüberg, Müller (b4) 2021; 5
Makitalo, Foi (b11) 2010; 20
P.G. Kumar, R. Ranjan Ranjan, Low rank Poisson denoising (LRPD) A low rank approach using split bregman algorithm for Poisson noise removal from images, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.
C.A. Deledalle, F. Tupin, L. Denis, Poisson NL means: Unsupervised non local means for Poisson noise, in: IEEE International Conference on Image Processing, 2010.
Qasim, Mohammed, Bayat (b7) 2022; 2022
Anscombe (b8) 1948; 35
Huang, Li, Jia, Lu, Liu (b22) 2022; 31
K. Bui, Y. Lou, F. Park, J. Xin, Weighted Anisotropic–Isotropic Total Variation for Poisson Denoising, in: 2023 IEEE International Conference on Image Processing, ICIP, 2023, pp. 1020–1024.
K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on Machine Learning, 2010, pp. 399–406.
Y. Chen, W. Yu, T. Pock, On learning optimized reaction diffusion processes for effective image restoration, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5261–5269.
Y. Sadamatsu, S. Murakami, G. Li, T. Kamiya, Denoising on Low-Dose CT Image Using Deep CNN, in: 2022 22nd International Conference on Control, Automation and Systems, ICCAS, 2022, pp. 546–549.
Fisz (b9) 1955; Vol. 3
Daubechies, Defrise, De Mol (b25) 2004; 57
Fryzlewicz, Nason (b10) 2004; 13
Remez, Litany, Giryes, Bronstein (b19) 2018; 27
Miller, Zhang, Hirakawa (b2) 2021; 30
Tolooshams, Song, Temereanca, Ba (b20) 2020
Salmon, Harmany, Deledalle, Willett (b12) 2014; 48
Tian, He, Liu, Ma (b3) 2022; 72
Boyd, Parikh, Chu, Peleato, Eckstein (b23) 2011; 3
H. Sreter, R. Giryes, Learned convolutional sparse coding, in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 2191–2195.
Giryes, Elad (b13) 2014; 23
Schmitt, Starck, Casandjian, Fadili, Grenier (b1) 2010; 517
Lecouat, Ponce, Mairal (b27) 2020
Ta, Aich, Gupta, Roy-Chowdhury (b5) 2022
10.1016/j.sigpro.2024.109870_b18
10.1016/j.sigpro.2024.109870_b17
Boyd (10.1016/j.sigpro.2024.109870_b23) 2011; 3
10.1016/j.sigpro.2024.109870_b14
Brinkmann (10.1016/j.sigpro.2024.109870_b4) 2021; 5
Qasim (10.1016/j.sigpro.2024.109870_b7) 2022; 2022
10.1016/j.sigpro.2024.109870_b15
10.1016/j.sigpro.2024.109870_b6
Simon (10.1016/j.sigpro.2024.109870_b21) 2019; 32
Tian (10.1016/j.sigpro.2024.109870_b3) 2022; 72
Makitalo (10.1016/j.sigpro.2024.109870_b11) 2010; 20
Lecouat (10.1016/j.sigpro.2024.109870_b27) 2020
Salmon (10.1016/j.sigpro.2024.109870_b12) 2014; 48
Huang (10.1016/j.sigpro.2024.109870_b22) 2022; 31
Ta (10.1016/j.sigpro.2024.109870_b5) 2022
Scetbon (10.1016/j.sigpro.2024.109870_b29) 2021; 30
10.1016/j.sigpro.2024.109870_b28
10.1016/j.sigpro.2024.109870_b24
Schmitt (10.1016/j.sigpro.2024.109870_b1) 2010; 517
10.1016/j.sigpro.2024.109870_b26
Fisz (10.1016/j.sigpro.2024.109870_b9) 1955; Vol. 3
Daubechies (10.1016/j.sigpro.2024.109870_b25) 2004; 57
Fryzlewicz (10.1016/j.sigpro.2024.109870_b10) 2004; 13
Remez (10.1016/j.sigpro.2024.109870_b19) 2018; 27
Miller (10.1016/j.sigpro.2024.109870_b2) 2021; 30
Anscombe (10.1016/j.sigpro.2024.109870_b8) 1948; 35
Tolooshams (10.1016/j.sigpro.2024.109870_b20) 2020
Zhao (10.1016/j.sigpro.2024.109870_b16) 2021; 15
Giryes (10.1016/j.sigpro.2024.109870_b13) 2014; 23
References_xml – volume: 57
  start-page: 1413
  year: 2004
  end-page: 1457
  ident: b25
  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.
– volume: 3
  start-page: 1
  year: 2011
  end-page: 122
  ident: b23
  article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers
  publication-title: Found. Trends® Mach. Learn.
– volume: 517
  year: 2010
  ident: b1
  article-title: Poisson denoising on the sphere: application to the Fermi gamma ray space telescope
  publication-title: Astron. Astrophys.
– reference: C.A. Deledalle, F. Tupin, L. Denis, Poisson NL means: Unsupervised non local means for Poisson noise, in: IEEE International Conference on Image Processing, 2010.
– volume: Vol. 3
  start-page: 138
  year: 1955
  end-page: 146
  ident: b9
  article-title: The limiting distribution of a function of two independent random variables and its statistical application
  publication-title: Colloquium Mathematicum
– reference: Y. Sadamatsu, S. Murakami, G. Li, T. Kamiya, Denoising on Low-Dose CT Image Using Deep CNN, in: 2022 22nd International Conference on Control, Automation and Systems, ICCAS, 2022, pp. 546–549.
– reference: H. Sreter, R. Giryes, Learned convolutional sparse coding, in: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 2191–2195.
– volume: 31
  start-page: 4023
  year: 2022
  end-page: 4038
  ident: b22
  article-title: Neighbor2neighbor: A self-supervised framework for deep image denoising
  publication-title: IEEE Trans. Image Process.
– volume: 20
  start-page: 99
  year: 2010
  end-page: 109
  ident: b11
  article-title: Optimal inversion of the Anscombe transformation in low-count Poisson image denoising
  publication-title: IEEE Trans. Image Process.
– reference: P.G. Kumar, R. Ranjan Ranjan, Low rank Poisson denoising (LRPD) A low rank approach using split bregman algorithm for Poisson noise removal from images, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.
– volume: 32
  year: 2019
  ident: b21
  article-title: Rethinking the CSC model for natural images
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 2022
  year: 2022
  ident: b7
  article-title: Breast sentinel lymph node cancer detection from mammographic images based on quantum wavelet transform and an atrous pyramid convolutional neural network
  publication-title: Sci. Program.
– start-page: 557
  year: 2022
  end-page: 567
  ident: b5
  article-title: Poisson2Sparse: Self-supervised Poisson denoising from a single image
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– volume: 13
  start-page: 621
  year: 2004
  end-page: 638
  ident: b10
  article-title: A Haar-Fisz algorithm for Poisson intensity estimation
  publication-title: J. Comput. Graph. Statist.
– reference: Y. Chen, W. Yu, T. Pock, On learning optimized reaction diffusion processes for effective image restoration, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5261–5269.
– volume: 15
  start-page: 519
  year: 2021
  ident: b16
  article-title: A nonlocal low rank model for Poisson noise removal
  publication-title: Inverse Probl. Imaging
– start-page: 9493
  year: 2020
  end-page: 9503
  ident: b20
  article-title: Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
  publication-title: International Conference on Machine Learning
– reference: K. Gregor, Y. LeCun, Learning fast approximations of sparse coding, in: Proceedings of the 27th International Conference on Machine Learning, 2010, pp. 399–406.
– start-page: 238
  year: 2020
  end-page: 254
  ident: b27
  article-title: Fully trainable and interpretable non-local sparse models for image restoration
  publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August (2020) 23–28, Proceedings, Part XXII 16
– reference: K. Bui, Y. Lou, F. Park, J. Xin, Weighted Anisotropic–Isotropic Total Variation for Poisson Denoising, in: 2023 IEEE International Conference on Image Processing, ICIP, 2023, pp. 1020–1024.
– volume: 48
  start-page: 279
  year: 2014
  end-page: 294
  ident: b12
  article-title: Poisson noise reduction with non-local PCA
  publication-title: J. Math. Imaging Vision
– volume: 30
  start-page: 5944
  year: 2021
  end-page: 5955
  ident: b29
  article-title: Deep k-svd denoising
  publication-title: IEEE Trans. Image Process.
– volume: 27
  start-page: 5707
  year: 2018
  end-page: 5722
  ident: b19
  article-title: Class-aware fully convolutional Gaussian and Poisson denoising
  publication-title: IEEE Trans. Image Process.
– volume: 72
  start-page: 1
  year: 2022
  end-page: 11
  ident: b3
  article-title: Interpretable Poisson optimization-inspired deep network for single-photon counting image denoising
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 35
  start-page: 246
  year: 1948
  end-page: 254
  ident: b8
  article-title: The transformation of Poisson, binomial and negative-binomial data
  publication-title: Biometrika
– volume: 5
  year: 2021
  ident: b4
  article-title: Advanced high dynamic range fluorescence microscopy with Poisson noise modeling and integrated edge-preserving denoising
  publication-title: J. Phys. Commun.
– reference: Z. Zha, B. Wen, X. Yuan, J. Zhou, C. Zhu, Simultaneous nonlocal low-rank and deep priors for Poisson denoising, in: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2022, pp. 2320–2324.
– volume: 23
  start-page: 5057
  year: 2014
  end-page: 5069
  ident: b13
  article-title: Sparsity-based Poisson denoising with dictionary learning
  publication-title: IEEE Trans. Image Process.
– volume: 30
  start-page: 5724
  year: 2021
  end-page: 5738
  ident: b2
  article-title: Multi-resolution aitchison geometry image denoising for low-light photography
  publication-title: IEEE Trans. Image Process.
– volume: Vol. 3
  start-page: 138
  year: 1955
  ident: 10.1016/j.sigpro.2024.109870_b9
  article-title: The limiting distribution of a function of two independent random variables and its statistical application
– volume: 72
  start-page: 1
  year: 2022
  ident: 10.1016/j.sigpro.2024.109870_b3
  article-title: Interpretable Poisson optimization-inspired deep network for single-photon counting image denoising
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 57
  start-page: 1413
  issue: 11
  year: 2004
  ident: 10.1016/j.sigpro.2024.109870_b25
  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
– start-page: 557
  year: 2022
  ident: 10.1016/j.sigpro.2024.109870_b5
  article-title: Poisson2Sparse: Self-supervised Poisson denoising from a single image
– ident: 10.1016/j.sigpro.2024.109870_b15
  doi: 10.1109/CVPRW.2019.00242
– start-page: 238
  year: 2020
  ident: 10.1016/j.sigpro.2024.109870_b27
  article-title: Fully trainable and interpretable non-local sparse models for image restoration
– ident: 10.1016/j.sigpro.2024.109870_b6
  doi: 10.23919/ICCAS55662.2022.10003847
– volume: 27
  start-page: 5707
  issue: 11
  year: 2018
  ident: 10.1016/j.sigpro.2024.109870_b19
  article-title: Class-aware fully convolutional Gaussian and Poisson denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2018.2859044
– ident: 10.1016/j.sigpro.2024.109870_b24
  doi: 10.1109/CVPR.2015.7299163
– volume: 5
  issue: 7
  year: 2021
  ident: 10.1016/j.sigpro.2024.109870_b4
  article-title: Advanced high dynamic range fluorescence microscopy with Poisson noise modeling and integrated edge-preserving denoising
  publication-title: J. Phys. Commun.
  doi: 10.1088/2399-6528/ac0eca
– volume: 517
  issue: A26
  year: 2010
  ident: 10.1016/j.sigpro.2024.109870_b1
  article-title: Poisson denoising on the sphere: application to the Fermi gamma ray space telescope
  publication-title: Astron. Astrophys.
– ident: 10.1016/j.sigpro.2024.109870_b28
– ident: 10.1016/j.sigpro.2024.109870_b18
  doi: 10.1109/ICIP.2010.5653394
– volume: 35
  start-page: 246
  issue: 3/4
  year: 1948
  ident: 10.1016/j.sigpro.2024.109870_b8
  article-title: The transformation of Poisson, binomial and negative-binomial data
  publication-title: Biometrika
  doi: 10.2307/2332343
– volume: 20
  start-page: 99
  issue: 1
  year: 2010
  ident: 10.1016/j.sigpro.2024.109870_b11
  article-title: Optimal inversion of the Anscombe transformation in low-count Poisson image denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2010.2056693
– ident: 10.1016/j.sigpro.2024.109870_b17
  doi: 10.1109/ICIP49359.2023.10222230
– start-page: 9493
  year: 2020
  ident: 10.1016/j.sigpro.2024.109870_b20
  article-title: Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
– ident: 10.1016/j.sigpro.2024.109870_b26
  doi: 10.1109/ICASSP.2018.8462313
– ident: 10.1016/j.sigpro.2024.109870_b14
  doi: 10.1109/ICASSP43922.2022.9746870
– volume: 13
  start-page: 621
  issue: 3
  year: 2004
  ident: 10.1016/j.sigpro.2024.109870_b10
  article-title: A Haar-Fisz algorithm for Poisson intensity estimation
  publication-title: J. Comput. Graph. Statist.
  doi: 10.1198/106186004X2697
– volume: 15
  start-page: 519
  issue: 3
  year: 2021
  ident: 10.1016/j.sigpro.2024.109870_b16
  article-title: A nonlocal low rank model for Poisson noise removal
  publication-title: Inverse Probl. Imaging
  doi: 10.3934/ipi.2021003
– volume: 30
  start-page: 5944
  year: 2021
  ident: 10.1016/j.sigpro.2024.109870_b29
  article-title: Deep k-svd denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3090531
– volume: 30
  start-page: 5724
  year: 2021
  ident: 10.1016/j.sigpro.2024.109870_b2
  article-title: Multi-resolution aitchison geometry image denoising for low-light photography
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2021.3087943
– volume: 3
  start-page: 1
  issue: 1
  year: 2011
  ident: 10.1016/j.sigpro.2024.109870_b23
  article-title: Distributed optimization and statistical learning via the alternating direction method of multipliers
  publication-title: Found. Trends® Mach. Learn.
– volume: 23
  start-page: 5057
  issue: 12
  year: 2014
  ident: 10.1016/j.sigpro.2024.109870_b13
  article-title: Sparsity-based Poisson denoising with dictionary learning
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2014.2362057
– volume: 48
  start-page: 279
  year: 2014
  ident: 10.1016/j.sigpro.2024.109870_b12
  article-title: Poisson noise reduction with non-local PCA
  publication-title: J. Math. Imaging Vision
  doi: 10.1007/s10851-013-0435-6
– volume: 31
  start-page: 4023
  year: 2022
  ident: 10.1016/j.sigpro.2024.109870_b22
  article-title: Neighbor2neighbor: A self-supervised framework for deep image denoising
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2022.3176533
– volume: 2022
  issue: 1
  year: 2022
  ident: 10.1016/j.sigpro.2024.109870_b7
  article-title: Breast sentinel lymph node cancer detection from mammographic images based on quantum wavelet transform and an atrous pyramid convolutional neural network
  publication-title: Sci. Program.
– volume: 32
  year: 2019
  ident: 10.1016/j.sigpro.2024.109870_b21
  article-title: Rethinking the CSC model for natural images
  publication-title: Adv. Neural Inf. Process. Syst.
SSID ssj0001360
Score 2.458141
Snippet In fields such as low-light photography, astronomical imaging, and low-dose computed tomography scanning, Poisson noise severely degrades image quality due to...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 109870
SubjectTerms Convolutional sparse coding
Image denoising
Poisson noise
Unfolding
Unsupervised learning
Title Poisson2Poisson-Sparse: Unsupervised Poisson noise image denoising based on sparse modeling
URI https://dx.doi.org/10.1016/j.sigpro.2024.109870
Volume 230
WOSCitedRecordID wos001420447600001&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: 0165-1684
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0001360
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF5BygEOqLxEoUV74FYtWr93uVVVEUSoqpQgInGw7H0krmBj1Qmq-uuZfdiJSMVL4mLHXu8mmfk0OzOeB0Kva10JGsmapDkDA6WKMlIJmRChcsV5VceZL5L0sTg_Z7MZvwi5J51rJ1AYw66veftfWQ33gNk2dfYv2D0sCjfgMzAdjsB2OP4R4y-WQMulicOZTFqwXV0G-ifTrVsrGzrQMsPwsYGzOm6-2dgdkEFwZZ0HdnOT9kVC52b7hjn9Lhd02Ukzt6ps61MN-kFg3qyplsHen98smo3PPrimF8rMa3hmx2k9Xg9Q_axcmMG4Wd8s1LZrIs42gYDeX7aTM-NdmHlGotw3hutlcOxfzuzIc-9auHzTNXP4N2DOx6ktgMV8s5GfKmVP7NJ2ZRsXm3JK76K9uMg4G6G9kw9ns_GwRUeJSx8ffkqfU-kC_3a_63adZUsPme6jh8GAwCee8Y_QHWUeowdbZSWfoC-3Q-At3gYADoPYAQA7AOABANgBAMOwBwDuAfAUTd-dTU_fk9BEgwiwBlckkXEsNZWaJ5raXmRU2HzpSNc6YaIA6zyTeZVQWShOa14wZZVSpXSUyVRHyTM0MkujniNcUaYLMH9rULpTJimr00SAxE8rW-RfFQco6alUilBg3vY5-Vr2kYSXpadtaWlbetoeIDLMan2Bld88X_QMKIOS6JW_EjDzy5kv_nnmS3R_A-9DNFpdrdURuie-r5ru6lUA1w--hJAt
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=Poisson2Poisson-Sparse%3A+Unsupervised+Poisson+noise+image+denoising+based+on+sparse+modeling&rft.jtitle=Signal+processing&rft.au=Xiao%2C+Lingzhi&rft.au=Wang%2C+Shengbiao&rft.au=Zhang%2C+Jun&rft.au=Wei%2C+Jiuzhe&rft.date=2025-05-01&rft.pub=Elsevier+B.V&rft.issn=0165-1684&rft.volume=230&rft_id=info:doi/10.1016%2Fj.sigpro.2024.109870&rft.externalDocID=S0165168424004900
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0165-1684&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0165-1684&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0165-1684&client=summon