Single-pixel imaging with untrained convolutional autoencoder network

•We propose a physical model-driven untrained deep convolutional autoencoder network for SPI and validate its performance from simulations and experiments.•We designed an end-to-end SPI reconstruction network, which can better reconstruct high-quality images from under-sampled measurements.•We perfo...

Full description

Saved in:

Bibliographic Details
Published in:	Optics and laser technology Vol. 167; p. 109710
Main Authors:	Li, Zhicai, Huang, Jian, Shi, Dongfeng, Chen, Yafeng, Yuan, Kee, Hu, Shunxing, Wang, Yingjian
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.12.2023
Subjects:	Convolutional neural network Deep learning Long-range imaging Single-pixel imaging Deep learning Single-pixel imaging Long-range imaging Convolutional neural network
ISSN:	0030-3992, 1879-2545
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	•We propose a physical model-driven untrained deep convolutional autoencoder network for SPI and validate its performance from simulations and experiments.•We designed an end-to-end SPI reconstruction network, which can better reconstruct high-quality images from under-sampled measurements.•We perform a comparative study through the simulations and experiments. The results demonstrate that UCAN outperforms other existed SPI methods, including DGI, TVAL3, and GIDC. Single-pixel imaging (SPI) is a novel imaging modality which captures the images with a single-pixel detector by using a lot of time-varying modulation patterns. Nowadays, SPI reconstructions with data-driven deep learning had been verified for high-quality reconstructions under low sampling ratios. However, it faces a dilemma of hard-to-get sufficient training sets in many practical applications, e.g., long-range single-pixel imaging fields. Here, a model-driven SPI reconstruction method based on untrained convolutional autoencoder network (UCAN) is proposed. This framework does not need to pre-train on any dataset and can be automatically optimized, then eventually produce the restored images through the interplay between the neural network and the SPI physical model. Simulations confirm the superiorities of the proposed method over many other existed algorithms in the SPI field. Also, the reconstructions for long-range single-pixel imaging in real urban atmospheric environments demonstrate that our method has better denoising performance. We believe that the present work provides an alternative framework for SPI and paves the way for practical applications, e.g., long-range optical remote sensing and low-irradiative biological imaging.
AbstractList	•We propose a physical model-driven untrained deep convolutional autoencoder network for SPI and validate its performance from simulations and experiments.•We designed an end-to-end SPI reconstruction network, which can better reconstruct high-quality images from under-sampled measurements.•We perform a comparative study through the simulations and experiments. The results demonstrate that UCAN outperforms other existed SPI methods, including DGI, TVAL3, and GIDC. Single-pixel imaging (SPI) is a novel imaging modality which captures the images with a single-pixel detector by using a lot of time-varying modulation patterns. Nowadays, SPI reconstructions with data-driven deep learning had been verified for high-quality reconstructions under low sampling ratios. However, it faces a dilemma of hard-to-get sufficient training sets in many practical applications, e.g., long-range single-pixel imaging fields. Here, a model-driven SPI reconstruction method based on untrained convolutional autoencoder network (UCAN) is proposed. This framework does not need to pre-train on any dataset and can be automatically optimized, then eventually produce the restored images through the interplay between the neural network and the SPI physical model. Simulations confirm the superiorities of the proposed method over many other existed algorithms in the SPI field. Also, the reconstructions for long-range single-pixel imaging in real urban atmospheric environments demonstrate that our method has better denoising performance. We believe that the present work provides an alternative framework for SPI and paves the way for practical applications, e.g., long-range optical remote sensing and low-irradiative biological imaging.
ArticleNumber	109710
Author	Shi, Dongfeng Huang, Jian Li, Zhicai Wang, Yingjian Hu, Shunxing Chen, Yafeng Yuan, Kee
Author_xml	– sequence: 1 givenname: Zhicai orcidid: 0000-0002-2946-4496 surname: Li fullname: Li, Zhicai organization: Institute of Material Science and Information Technology, Anhui University, Hefei 230601, China – sequence: 2 givenname: Jian orcidid: 0000-0002-6114-5815 surname: Huang fullname: Huang, Jian email: jhuang@aiofm.ac.cn organization: Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China – sequence: 3 givenname: Dongfeng surname: Shi fullname: Shi, Dongfeng organization: Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China – sequence: 4 givenname: Yafeng surname: Chen fullname: Chen, Yafeng organization: Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China – sequence: 5 givenname: Kee surname: Yuan fullname: Yuan, Kee organization: Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China – sequence: 6 givenname: Shunxing surname: Hu fullname: Hu, Shunxing organization: Institute of Material Science and Information Technology, Anhui University, Hefei 230601, China – sequence: 7 givenname: Yingjian surname: Wang fullname: Wang, Yingjian organization: Key Laboratory of Atmospheric Optics, Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China
BookMark	eNqNkMtOwzAQRS1UJErhG8gPpIzjOLEXLKqqPKRKLIC15djT4hLsynFb-HsSFbFgA6vRjHSu5p5zMvLBIyFXFKYUaHW9mYZtanWX0EwLKFh_lTWFEzKmopZ5wUs-ImMABjmTsjgj5123AYCy4mxMFk_Or1vMt-4D28y963W_ZweXXrOdT1E7jzYzwe9Du0sueN1mepcCehMsxsxjOoT4dkFOV7rt8PJ7TsjL7eJ5fp8vH-8e5rNlbhjlKTelNKJBKlHIckWpFqKwKAxCVVGwALqGBnndaGml1aIWmhdUcF2yRkCBbELqY66JoesirtQ29j_HT0VBDTbURv3YUIMNdbTRkze_SOOSHhoNJdt_8LMjj329vcOoOuN6C2hdRJOUDe7PjC-22YVE
CitedBy_id	crossref_primary_10_3390_electronics14071355 crossref_primary_10_3390_photonics12020164 crossref_primary_10_3390_app15147717 crossref_primary_10_3390_s24248139 crossref_primary_10_3788_LOP250831 crossref_primary_10_1088_0256_307X_41_12_124202
Cites_doi	10.1109/CVPR.2018.00984 10.1016/j.optlastec.2022.108140 10.1103/PhysRevLett.104.253603 10.1007/978-3-319-24574-4_28 10.1016/j.optlaseng.2022.107101 10.1038/s41377-020-0302-3 10.1364/OPTICA.389314 10.1016/j.optlaseng.2021.106744 10.1364/OPTICA.1.000285 10.1038/s41598-020-68401-8 10.1364/OE.25.019619 10.1364/OE.472171 10.1103/PhysRevA.52.R3429 10.3390/s19194190 10.1038/s41598-017-03725-6 10.1016/j.optcom.2017.12.041 10.1038/s41377-021-00680-w 10.1364/OE.27.025560 10.1364/OE.385233 10.1364/OE.421354 10.1109/TIP.2012.2188033 10.3390/s19030732 10.1103/PhysRevA.78.061802 10.1364/PRJ.440123 10.1126/science.1234454 10.1103/PhysRevLett.117.113901 10.1016/j.optlaseng.2020.106183 10.1016/j.optlaseng.2023.107580 10.1016/j.optlaseng.2022.107141 10.1364/OE.24.026080 10.1063/1.3238296 10.1016/j.optlastec.2015.12.009 10.1364/OE.25.022859 10.1364/OE.471036
ContentType	Journal Article
Copyright	2023 Elsevier Ltd
Copyright_xml	– notice: 2023 Elsevier Ltd
DBID	AAYXX CITATION
DOI	10.1016/j.optlastec.2023.109710
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1879-2545
ExternalDocumentID	10_1016_j_optlastec_2023_109710 S0030399223006035
GroupedDBID	--K --M -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABXZ AACTN AAEDT AAEDW AAEPC AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO ABJNI ABMAC ABNEU ABXDB ABXRA ABYKQ ACBEA ACDAQ ACFVG ACGFO ACGFS ACIWK ACNNM ACRLP ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEKER AENEX AEZYN AFFNX AFKWA AFRZQ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AIEXJ AIKHN AITUG AIVDX AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ASPBG AVWKF AXJTR AZFZN BBWZM BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA HMV HVGLF HZ~ IHE J1W JJJVA KOM LY7 M38 M41 MAGPM MO0 N9A NDZJH O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SET SEW SPC SPCBC SPD SPG SSM SSQ SST SSZ T5K TN5 UHS WH7 WUQ XFK ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD
ID	FETCH-LOGICAL-c315t-c49c8be19e894f11a882de8ce06610d00a70be57ba9d9da878a52185a43b802e3
ISICitedReferencesCount	17
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001026404500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0030-3992
IngestDate	Tue Nov 18 20:41:46 EST 2025 Sat Nov 29 07:31:37 EST 2025 Fri Feb 23 02:37:23 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Deep learning Single-pixel imaging Long-range imaging Convolutional neural network
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c315t-c49c8be19e894f11a882de8ce06610d00a70be57ba9d9da878a52185a43b802e3
ORCID	0000-0002-6114-5815 0000-0002-2946-4496
ParticipantIDs	crossref_primary_10_1016_j_optlastec_2023_109710 crossref_citationtrail_10_1016_j_optlastec_2023_109710 elsevier_sciencedirect_doi_10_1016_j_optlastec_2023_109710
PublicationCentury	2000
PublicationDate	December 2023 2023-12-00
PublicationDateYYYYMMDD	2023-12-01
PublicationDate_xml	– month: 12 year: 2023 text: December 2023
PublicationDecade	2020
PublicationTitle	Optics and laser technology
PublicationYear	2023
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Rizvi, Cao, Zhang, Hao (b0100) 2020; 10 Zhang, Wang, Zheng, Zhong (b0060) 2017; 25 Gong (b0015) 2022; 152 Zhou, Liu, Feng, Li, Wang, Sun, Huang, Song (b0095) 2022; 156 Brás, Bioucas-Dias, Martins, Serra (b0165) 2012; 21 Rizvi, Cao, Zhang, Hao (b0075) 2019; 19 Wang, Bian, Wang, Lyu, Pedrini, Osten, Barbastathis, Situ (b0115) 2020; 9 Wang, Wang, Deng, Han, Situ (b0150) 2022; 10 Katz, Bromberg, Silberberg (b0055) 2009; 95 Chen, Wei, Chen, Dong (b0145) 2021; 29 Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Liu, Meng, Yin, Wu, Jiang (b0160) 2021; 147 Rizvi, Cao, Zhang, Hao (b0105) 2020; 28 Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 Wu, Wang, Zhao, Xiao, Liang, Wang, Tian, Cheng, Zhang (b0090) 2020; 134 Ferri, Magatti, Lugiato, Gatti (b0130) 2010; 104 Sun, Edgar, Bowman, Vittert, Welsh, Bowman, Padgett (b0045) 2013; 340 Cao, Xiao, Pan, Zhou, Chen (b0040) 2022; 158 Huang, Li, Shi, Chen, Yuan, Hu, Wang (b0175) 2022; 30 Shapiro (b0010) 2008; 78 (pp. 234-241). Springer International Publishing. Vasile, Damian, Coltuc, Petrovici (b0030) 2016; 79 Sun, Zhang (b0050) 2019; 19 Le, Wang, Zheng, Liu, Zhou, Xu (b0035) 2017; 25 Sun, Meng, Edgar, Padgett, Radwell (b0170) 2017; 7 Yu, Lu, Han, Xie, Du, Xiao, Zhu (b0020) 2016; 117 Bostan, Heckel, Chen, Kellman, Waller (b0140) 2020; 7 Li, Wu, Liu, Zhang (b0155) 2023; 166 Pittman, Shih, Strekalov, Sergienko (b0005) 1995; 52 Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2018). Deep image prior. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9446-9454). Zhang, Ma, Zhong (b0065) 2015; 6 Chen, Huang, Chen (b0135) 2022; 30 Shimobaba, Endo, Nishitsuji, Takahashi, Nagahama, Hasegawa, Sano, Hirayama, Kakue, Shiraki (b0080) 2018; 413 Wang, Wang, Wang, Li, Situ (b0085) 2019; 27 Radwell, Mitchell, Gibson, Edgar, Bowman, Padgett (b0025) 2014; 1 Dai, Gu, He, Ye, Mao, Chen (b0070) 2016; 24 Wang, Wang, Chen, Gong, Zhang, Han, Situ (b0120) 2022; 11 Cao (10.1016/j.optlastec.2023.109710_b0040) 2022; 158 Wu (10.1016/j.optlastec.2023.109710_b0090) 2020; 134 Chen (10.1016/j.optlastec.2023.109710_b0145) 2021; 29 Li (10.1016/j.optlastec.2023.109710_b0155) 2023; 166 Shapiro (10.1016/j.optlastec.2023.109710_b0010) 2008; 78 Huang (10.1016/j.optlastec.2023.109710_b0175) 2022; 30 Yu (10.1016/j.optlastec.2023.109710_b0020) 2016; 117 Zhang (10.1016/j.optlastec.2023.109710_b0060) 2017; 25 Radwell (10.1016/j.optlastec.2023.109710_b0025) 2014; 1 Le (10.1016/j.optlastec.2023.109710_b0035) 2017; 25 Shimobaba (10.1016/j.optlastec.2023.109710_b0080) 2018; 413 Katz (10.1016/j.optlastec.2023.109710_b0055) 2009; 95 10.1016/j.optlastec.2023.109710_b0125 Rizvi (10.1016/j.optlastec.2023.109710_b0100) 2020; 10 Wang (10.1016/j.optlastec.2023.109710_b0115) 2020; 9 Ferri (10.1016/j.optlastec.2023.109710_b0130) 2010; 104 Pittman (10.1016/j.optlastec.2023.109710_b0005) 1995; 52 Rizvi (10.1016/j.optlastec.2023.109710_b0075) 2019; 19 Wang (10.1016/j.optlastec.2023.109710_b0085) 2019; 27 Sun (10.1016/j.optlastec.2023.109710_b0170) 2017; 7 Sun (10.1016/j.optlastec.2023.109710_b0050) 2019; 19 Zhou (10.1016/j.optlastec.2023.109710_b0095) 2022; 156 Wang (10.1016/j.optlastec.2023.109710_b0120) 2022; 11 Liu (10.1016/j.optlastec.2023.109710_b0160) 2021; 147 Gong (10.1016/j.optlastec.2023.109710_b0015) 2022; 152 Bostan (10.1016/j.optlastec.2023.109710_b0140) 2020; 7 Brás (10.1016/j.optlastec.2023.109710_b0165) 2012; 21 Vasile (10.1016/j.optlastec.2023.109710_b0030) 2016; 79 Chen (10.1016/j.optlastec.2023.109710_b0135) 2022; 30 Dai (10.1016/j.optlastec.2023.109710_b0070) 2016; 24 10.1016/j.optlastec.2023.109710_b0110 Sun (10.1016/j.optlastec.2023.109710_b0045) 2013; 340 Zhang (10.1016/j.optlastec.2023.109710_b0065) 2015; 6 Wang (10.1016/j.optlastec.2023.109710_b0150) 2022; 10 Rizvi (10.1016/j.optlastec.2023.109710_b0105) 2020; 28
References_xml	– volume: 21 start-page: 3004 year: 2012 end-page: 3016 ident: b0165 article-title: An alternating direction algorithm for total variation reconstruction of distributed parameters publication-title: IEEE Trans. Image Process. – volume: 104 year: 2010 ident: b0130 article-title: Differential ghost imaging publication-title: Phys. Rev. Lett. – volume: 147 year: 2021 ident: b0160 article-title: Computational ghost imaging based on an untrained neural network publication-title: Opt. Lasers Eng. – volume: 30 start-page: 39597 year: 2022 end-page: 39612 ident: b0135 article-title: Fourier ptychographic microscopy with untrained deep neural network priors publication-title: Opt. Express – volume: 166 year: 2023 ident: b0155 article-title: URNet: High-quality single-pixel imaging with untrained reconstruction network publication-title: Opt. Lasers Eng. – volume: 52 start-page: R3429 year: 1995 ident: b0005 article-title: Optical imaging by means of two-photon quantum entanglement publication-title: Phys. Rev. A – volume: 78 year: 2008 ident: b0010 article-title: Computational ghost imaging publication-title: Phys. Rev. A – volume: 152 year: 2022 ident: b0015 article-title: Performance comparison of computational ghost imaging versus single-pixel camera in light disturbance environment publication-title: Opt. Laser Technol. – volume: 95 year: 2009 ident: b0055 article-title: Compressive ghost imaging publication-title: Appl. Phys. Lett. – volume: 27 start-page: 25560 year: 2019 end-page: 25572 ident: b0085 article-title: Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging publication-title: Opt. Express – volume: 10 start-page: 104 year: 2022 end-page: 110 ident: b0150 article-title: Single-pixel imaging using physics enhanced deep learning publication-title: Photonics Res. – volume: 19 start-page: 4190 year: 2019 ident: b0075 article-title: Improving imaging quality of real-time Fourier single-pixel imaging via deep learning publication-title: Sensors – volume: 134 year: 2020 ident: b0090 article-title: Deep-learning denoising computational ghost imaging publication-title: Opt. Lasers Eng. – volume: 24 start-page: 26080 year: 2016 end-page: 26096 ident: b0070 article-title: Adaptive compressed photon counting 3D imaging based on wavelet trees and depth map sparse representation publication-title: Opt. Express – volume: 30 start-page: 37484 year: 2022 end-page: 37492 ident: b0175 article-title: Scanning single-pixel imaging lidar publication-title: Opt. Express – reference: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 – volume: 340 start-page: 844 year: 2013 end-page: 847 ident: b0045 article-title: 3D computational imaging with single-pixel detectors publication-title: Science – volume: 28 start-page: 7360 year: 2020 end-page: 7374 ident: b0105 article-title: Deringing and denoising in extremely under-sampled Fourier single pixel imaging publication-title: Opt. Express – reference: Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In – reference: (pp. 234-241). Springer International Publishing. – volume: 158 year: 2022 ident: b0040 article-title: Direct generation of 2D arrays of random numbers for high-fidelity optical ghost diffraction and information transmission through scattering media publication-title: Opt. Lasers Eng. – volume: 7 start-page: 559 year: 2020 end-page: 562 ident: b0140 article-title: Deep phase decoder: self-calibrating phase microscopy with an untrained deep neural network publication-title: Optica – volume: 10 start-page: 1 year: 2020 end-page: 9 ident: b0100 article-title: DeepGhost: real-time computational ghost imaging via deep learning publication-title: Sci. Rep. – volume: 156 year: 2022 ident: b0095 article-title: Real-time physical compression computational ghost imaging based on array spatial light field modulation and deep learning publication-title: Opt. Lasers Eng. – volume: 25 start-page: 19619 year: 2017 end-page: 19639 ident: b0060 article-title: Hadamard single-pixel imaging versus Fourier single-pixel imaging publication-title: Opt. Express – reference: Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2018). Deep image prior. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 9446-9454). – volume: 11 start-page: 1 year: 2022 ident: b0120 article-title: Far-field super-resolution ghost imaging with a deep neural network constraint publication-title: Light Sci. Appl. – volume: 79 start-page: 173 year: 2016 end-page: 178 ident: b0030 article-title: Single pixel sensing for THz laser beam profiler based on Hadamard Transform publication-title: Opt. Laser Technol. – volume: 7 start-page: 3464 year: 2017 ident: b0170 article-title: A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imaging publication-title: Sci. Rep. – volume: 413 start-page: 147 year: 2018 end-page: 151 ident: b0080 article-title: Computational ghost imaging using deep learning publication-title: Opt. Commun. – volume: 1 start-page: 285 year: 2014 end-page: 289 ident: b0025 article-title: Single-pixel infrared and visible microscope publication-title: Optica – volume: 117 year: 2016 ident: b0020 article-title: Fourier-transform ghost imaging with hard X rays publication-title: Phys. Rev. Lett. – volume: 6 start-page: 1 year: 2015 end-page: 6 ident: b0065 article-title: Single-pixel imaging by means of Fourier spectrum acquisition publication-title: Nat. Commun. – volume: 9 start-page: 1 year: 2020 end-page: 7 ident: b0115 article-title: Phase imaging with an untrained neural network publication-title: Light Sci. Appl. – volume: 25 start-page: 22859 year: 2017 end-page: 22868 ident: b0035 article-title: Underwater computational ghost imaging publication-title: Opt. Express – volume: 19 start-page: 732 year: 2019 ident: b0050 article-title: Single-pixel imaging and its application in three-dimensional reconstruction: A brief review publication-title: Sensors – volume: 29 start-page: 13011 year: 2021 end-page: 13024 ident: b0145 article-title: Focus shaping of high numerical aperture lens using physics-assisted artificial neural networks publication-title: Opt. Express – ident: 10.1016/j.optlastec.2023.109710_b0110 doi: 10.1109/CVPR.2018.00984 – volume: 152 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0015 article-title: Performance comparison of computational ghost imaging versus single-pixel camera in light disturbance environment publication-title: Opt. Laser Technol. doi: 10.1016/j.optlastec.2022.108140 – volume: 104 year: 2010 ident: 10.1016/j.optlastec.2023.109710_b0130 article-title: Differential ghost imaging publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.104.253603 – ident: 10.1016/j.optlastec.2023.109710_b0125 doi: 10.1007/978-3-319-24574-4_28 – volume: 156 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0095 article-title: Real-time physical compression computational ghost imaging based on array spatial light field modulation and deep learning publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2022.107101 – volume: 9 start-page: 1 year: 2020 ident: 10.1016/j.optlastec.2023.109710_b0115 article-title: Phase imaging with an untrained neural network publication-title: Light Sci. Appl. doi: 10.1038/s41377-020-0302-3 – volume: 6 start-page: 1 year: 2015 ident: 10.1016/j.optlastec.2023.109710_b0065 article-title: Single-pixel imaging by means of Fourier spectrum acquisition publication-title: Nat. Commun. – volume: 7 start-page: 559 year: 2020 ident: 10.1016/j.optlastec.2023.109710_b0140 article-title: Deep phase decoder: self-calibrating phase microscopy with an untrained deep neural network publication-title: Optica doi: 10.1364/OPTICA.389314 – volume: 147 year: 2021 ident: 10.1016/j.optlastec.2023.109710_b0160 article-title: Computational ghost imaging based on an untrained neural network publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2021.106744 – volume: 1 start-page: 285 year: 2014 ident: 10.1016/j.optlastec.2023.109710_b0025 article-title: Single-pixel infrared and visible microscope publication-title: Optica doi: 10.1364/OPTICA.1.000285 – volume: 10 start-page: 1 year: 2020 ident: 10.1016/j.optlastec.2023.109710_b0100 article-title: DeepGhost: real-time computational ghost imaging via deep learning publication-title: Sci. Rep. doi: 10.1038/s41598-020-68401-8 – volume: 25 start-page: 19619 year: 2017 ident: 10.1016/j.optlastec.2023.109710_b0060 article-title: Hadamard single-pixel imaging versus Fourier single-pixel imaging publication-title: Opt. Express doi: 10.1364/OE.25.019619 – volume: 30 start-page: 39597 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0135 article-title: Fourier ptychographic microscopy with untrained deep neural network priors publication-title: Opt. Express doi: 10.1364/OE.472171 – volume: 52 start-page: R3429 year: 1995 ident: 10.1016/j.optlastec.2023.109710_b0005 article-title: Optical imaging by means of two-photon quantum entanglement publication-title: Phys. Rev. A doi: 10.1103/PhysRevA.52.R3429 – volume: 19 start-page: 4190 issue: 19 year: 2019 ident: 10.1016/j.optlastec.2023.109710_b0075 article-title: Improving imaging quality of real-time Fourier single-pixel imaging via deep learning publication-title: Sensors doi: 10.3390/s19194190 – volume: 7 start-page: 3464 issue: 1 year: 2017 ident: 10.1016/j.optlastec.2023.109710_b0170 article-title: A Russian Dolls ordering of the Hadamard basis for compressive single-pixel imaging publication-title: Sci. Rep. doi: 10.1038/s41598-017-03725-6 – volume: 413 start-page: 147 year: 2018 ident: 10.1016/j.optlastec.2023.109710_b0080 article-title: Computational ghost imaging using deep learning publication-title: Opt. Commun. doi: 10.1016/j.optcom.2017.12.041 – volume: 11 start-page: 1 issue: 1 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0120 article-title: Far-field super-resolution ghost imaging with a deep neural network constraint publication-title: Light Sci. Appl. doi: 10.1038/s41377-021-00680-w – volume: 27 start-page: 25560 year: 2019 ident: 10.1016/j.optlastec.2023.109710_b0085 article-title: Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging publication-title: Opt. Express doi: 10.1364/OE.27.025560 – volume: 28 start-page: 7360 year: 2020 ident: 10.1016/j.optlastec.2023.109710_b0105 article-title: Deringing and denoising in extremely under-sampled Fourier single pixel imaging publication-title: Opt. Express doi: 10.1364/OE.385233 – volume: 29 start-page: 13011 year: 2021 ident: 10.1016/j.optlastec.2023.109710_b0145 article-title: Focus shaping of high numerical aperture lens using physics-assisted artificial neural networks publication-title: Opt. Express doi: 10.1364/OE.421354 – volume: 21 start-page: 3004 year: 2012 ident: 10.1016/j.optlastec.2023.109710_b0165 article-title: An alternating direction algorithm for total variation reconstruction of distributed parameters publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2012.2188033 – volume: 19 start-page: 732 year: 2019 ident: 10.1016/j.optlastec.2023.109710_b0050 article-title: Single-pixel imaging and its application in three-dimensional reconstruction: A brief review publication-title: Sensors doi: 10.3390/s19030732 – volume: 78 year: 2008 ident: 10.1016/j.optlastec.2023.109710_b0010 article-title: Computational ghost imaging publication-title: Phys. Rev. A doi: 10.1103/PhysRevA.78.061802 – volume: 10 start-page: 104 issue: 1 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0150 article-title: Single-pixel imaging using physics enhanced deep learning publication-title: Photonics Res. doi: 10.1364/PRJ.440123 – volume: 340 start-page: 844 year: 2013 ident: 10.1016/j.optlastec.2023.109710_b0045 article-title: 3D computational imaging with single-pixel detectors publication-title: Science doi: 10.1126/science.1234454 – volume: 117 year: 2016 ident: 10.1016/j.optlastec.2023.109710_b0020 article-title: Fourier-transform ghost imaging with hard X rays publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.117.113901 – volume: 134 year: 2020 ident: 10.1016/j.optlastec.2023.109710_b0090 article-title: Deep-learning denoising computational ghost imaging publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2020.106183 – volume: 166 year: 2023 ident: 10.1016/j.optlastec.2023.109710_b0155 article-title: URNet: High-quality single-pixel imaging with untrained reconstruction network publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2023.107580 – volume: 158 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0040 article-title: Direct generation of 2D arrays of random numbers for high-fidelity optical ghost diffraction and information transmission through scattering media publication-title: Opt. Lasers Eng. doi: 10.1016/j.optlaseng.2022.107141 – volume: 24 start-page: 26080 year: 2016 ident: 10.1016/j.optlastec.2023.109710_b0070 article-title: Adaptive compressed photon counting 3D imaging based on wavelet trees and depth map sparse representation publication-title: Opt. Express doi: 10.1364/OE.24.026080 – volume: 95 year: 2009 ident: 10.1016/j.optlastec.2023.109710_b0055 article-title: Compressive ghost imaging publication-title: Appl. Phys. Lett. doi: 10.1063/1.3238296 – volume: 79 start-page: 173 year: 2016 ident: 10.1016/j.optlastec.2023.109710_b0030 article-title: Single pixel sensing for THz laser beam profiler based on Hadamard Transform publication-title: Opt. Laser Technol. doi: 10.1016/j.optlastec.2015.12.009 – volume: 25 start-page: 22859 year: 2017 ident: 10.1016/j.optlastec.2023.109710_b0035 article-title: Underwater computational ghost imaging publication-title: Opt. Express doi: 10.1364/OE.25.022859 – volume: 30 start-page: 37484 year: 2022 ident: 10.1016/j.optlastec.2023.109710_b0175 article-title: Scanning single-pixel imaging lidar publication-title: Opt. Express doi: 10.1364/OE.471036
SSID	ssj0004653
Score	2.4425032
Snippet	•We propose a physical model-driven untrained deep convolutional autoencoder network for SPI and validate its performance from simulations and experiments.•We...
SourceID	crossref elsevier
SourceType	Enrichment Source Index Database Publisher
StartPage	109710
SubjectTerms	Convolutional neural network Deep learning Long-range imaging Single-pixel imaging
Title	Single-pixel imaging with untrained convolutional autoencoder network
URI	https://dx.doi.org/10.1016/j.optlastec.2023.109710
Volume	167
WOSCitedRecordID	wos001026404500001&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 customDbUrl: eissn: 1879-2545 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004653 issn: 0030-3992 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3PT9swFH6CAhI7TMCGgA2Uw25TqiROiM0NTZ0GQjCpMBUuUew4UFTSiKaof_6efzRNAQkQ4hJVVlw7fp-fn63P3wP4IRATmeAUwRvtu2HOcc6FNHVxaeYhriiSaDmGfyfx6Snt9dhfy58f6XQCcVHQyYSVH2pqLENjq6uzbzB3_adYgL_R6PhEs-PzVYbv4mI0kG7Zn8jBz_6dyUKkj1vHhU4IITPNNbedUFoB42qo9CyVrERhaOHNmPWsrKWcMdTGd6onx_EnmhNwpWgd_RlQ7FH0cQOB3RtzsX1YXOfSLpqaXGC832Val9qTiIA8YnXUV2RmfCTtcgk6emYS3rWl8bI0Zi7uTKM5N2zScjxx6eZ04bY9LCv8SPzCtmpbS29aQuy8XnZXtajldokSmyHRIiwFccRoC5YOjzq948a1WStSans4R_97trnng5dGQHK-Bp_tTsI5NAhYhwVZbMCnhr7kBqxofq8YfYFOExWORYWjUOHUqHDmUOE0UOFYVHyFi9-d819_XJtBwxXEjypXhExQLn0mKQtz309xP5VJKiQGmr6XeV4ae1xGMU9ZxrKUxjTFcI5GKc5U6gWSbEKrGBZyC5yQ-nkeBZmX4yTmfsB5HgdhxhknRHAmtmF_OjSJsPLyqvuDZMojvE3qMU3UmCZmTLfBqyuWRmHl5SoH07FPbKBoAsAEQfNS5Z33VP4GqzPkf4dWdT-Wu7AsHqr-6H7PAuw_036T1A
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=Single-pixel+imaging+with+untrained+convolutional+autoencoder+network&rft.jtitle=Optics+and+laser+technology&rft.au=Li%2C+Zhicai&rft.au=Huang%2C+Jian&rft.au=Shi%2C+Dongfeng&rft.au=Chen%2C+Yafeng&rft.date=2023-12-01&rft.pub=Elsevier+Ltd&rft.issn=0030-3992&rft.eissn=1879-2545&rft.volume=167&rft_id=info:doi/10.1016%2Fj.optlastec.2023.109710&rft.externalDocID=S0030399223006035
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0030-3992&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0030-3992&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0030-3992&client=summon