Plug-and-Play Algorithms for Video Snapshot Compressive Imaging

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated i...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on pattern analysis and machine intelligence Ročník 44; číslo 10; s. 7093 - 7111
Hlavní autori:	Yuan, Xin, Liu, Yang, Suo, Jinli, Durand, Fredo, Dai, Qionghai
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.10.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Algorithms Cameras coded aperture coded aperture compressive temporal imaging (CACTI) Color Compressive sensing computational imaging deep learning Frames (data processing) Gray-scale High speed Image coding Image color analysis image processing Image reconstruction Iterative methods Low speed Machine learning Noise reduction Optimization plug-and-play (PnP) algorithms Plugs Sensors Video compression video processing
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm.
AbstractList	We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm.We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm.
Author	Yuan, Xin Suo, Jinli Liu, Yang Dai, Qionghai Durand, Fredo
Author_xml	– sequence: 1 givenname: Xin orcidid: 0000-0002-8311-7524 surname: Yuan fullname: Yuan, Xin email: xyuan@westlake.edu.cn organization: School of Engineering, Westlake University, Hangzhou, Zhejiang, China – sequence: 2 givenname: Yang orcidid: 0000-0002-5787-0934 surname: Liu fullname: Liu, Yang email: yliu12@mit.edu organization: Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA – sequence: 3 givenname: Jinli orcidid: 0000-0002-3426-1634 surname: Suo fullname: Suo, Jinli email: jlsuo@tsinghua.edu.cn organization: Department of Automation, Tsinghua University, Beijing, China – sequence: 4 givenname: Fredo surname: Durand fullname: Durand, Fredo email: fredo@mit.edu organization: Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA – sequence: 5 givenname: Qionghai orcidid: 0000-0001-7043-3061 surname: Dai fullname: Dai, Qionghai email: qhdai@tsinghua.edu.cn organization: Department of Automation, Tsinghua University, Beijing, China
BookMark	eNp9kEtLw0AURgdRtFb_gG4Cbtyk3nmlMyspxUdBseBjO9wkkzolydSZVPDfG21x0YWruznn43KOyX7rW0vIGYURpaCvXuaTx9mIAaMjDloDl3tkwGgGqWaa7ZMB0IylSjF1RI5jXAJQIYEfkiMuOAWm1IBcz-v1IsW2TOc1fiWTeuGD696bmFQ-JG-utD55bnEV332XTH2zCjZG92mTWYML1y5OyEGFdbSn2zskr7c3L9P79OHpbjadPKQFZ6pLtYKS5UircYEyF5VVosiVKKFCndGCoRBY5VQKCgLLshQWcwUyy4sKlR0rPiSXm91V8B9rGzvTuFjYusbW-nU0TEqZcaWV7NGLHXTp16HtvzNsTIXq4wDvKbWhiuBjDLYyheuwc77tArraUDA_kc1vZPMT2Wwj9yrbUVfBNRi-_pfON5Kz1v4JWmhJteDfGDCH9Q
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1109_ACCESS_2025_3538499 crossref_primary_10_3390_rs16234601 crossref_primary_10_1007_s11263_023_01777_y crossref_primary_10_1016_j_optlastec_2025_113757 crossref_primary_10_1364_OL_555833 crossref_primary_10_1038_s41467_025_59104_7 crossref_primary_10_1364_AO_510414 crossref_primary_10_1109_TGRS_2023_3347220 crossref_primary_10_1016_j_optlastec_2025_113913 crossref_primary_10_1137_25M1723979 crossref_primary_10_1016_j_asoc_2024_111420 crossref_primary_10_1364_OPTICA_573166 crossref_primary_10_1021_acsphotonics_4c02003 crossref_primary_10_1364_OE_545510 crossref_primary_10_1109_TCI_2023_3237175 crossref_primary_10_1109_TPAMI_2023_3265103 crossref_primary_10_1109_TCI_2023_3241551 crossref_primary_10_1016_j_apm_2024_115645 crossref_primary_10_1109_TCI_2024_3477262 crossref_primary_10_1109_TNNLS_2024_3400809 crossref_primary_10_1109_TCSVT_2025_3543569 crossref_primary_10_1109_TPAMI_2024_3357704 crossref_primary_10_1016_j_optcom_2023_130010 crossref_primary_10_1049_ipr2_70024 crossref_primary_10_1109_TPAMI_2022_3161934 crossref_primary_10_1007_s11263_021_01532_1 crossref_primary_10_1364_PRJ_515895 crossref_primary_10_1364_PRJ_555010 crossref_primary_10_1016_j_neucom_2025_130803 crossref_primary_10_1117_1_JBO_29_S1_S11524 crossref_primary_10_1109_TPAMI_2022_3225382 crossref_primary_10_1007_s12596_022_00893_1 crossref_primary_10_1007_s00371_024_03700_z crossref_primary_10_1186_s43074_022_00065_1 crossref_primary_10_1109_JPROC_2023_3338272 crossref_primary_10_1109_TIM_2025_3593593
Cites_doi	10.1364/OE.25.018182 10.1109/TPAMI.2018.2817496 10.1364/OL.386238 10.1137/080716542 10.1137/17M1122451 10.1109/ICCV.2011.6126254 10.1109/CVPR.2014.424 10.1109/TCI.2016.2629286 10.1109/TIP.2006.884928 10.1117/12.766768 10.1109/ICIP.2016.7532817 10.1109/TSP.2006.881199 10.1109/MSP.2007.914730 10.1364/OE.17.006368 10.1007/978-3-030-01249-6_39 10.1145/2487575.2487586 10.1109/TIP.2007.901238 10.1109/CVPR.2011.5995542 10.1109/TIP.2017.2713099 10.1364/AOP.10.000409 10.1063/1.5140721 10.1364/OL.40.004054 10.1109/CVPR46437.2021.01595 10.1364/BOE.7.000746 10.1364/PRJ.411745 10.1109/TIP.2020.3005515 10.1109/TIP.2003.819861 10.1109/TPAMI.2019.2946567 10.1109/TIT.2019.2940666 10.1109/MSP.2020.3023869 10.1126/science.aat2298 10.1007/978-3-030-58592-1_12 10.1364/OPTICA.5.000127 10.1364/OPTICA.2.000822 10.1109/CVPR42600.2020.00152 10.1007/978-3-030-58586-0_16 10.1109/TIP.2020.2972109 10.1364/AOP.7.000756 10.1364/AO.55.007556 10.1109/TIP.2007.909319 10.1016/0167-2789(92)90242-f 10.1109/TCI.2016.2599778 10.1109/TIT.2006.871582 10.1109/ICCV.2009.5459452 10.1137/130936658 10.1109/TPAMI.2018.2873587 10.1109/CVPR.2014.366 10.1109/CVPR46437.2021.01598 10.1109/TIP.2014.2344294 10.1109/TIP.2012.2199324 10.1109/ICCV.2019.00416 10.1109/ICCV.2019.01032 10.1364/OE.23.011912 10.1109/ICASSP.2004.1326587 10.1109/TIP.2014.2365720 10.1109/ICIP.2013.6738004 10.1364/OL.420139 10.1109/CVPR42600.2020.00143 10.1364/AOP.398263 10.1109/JSTSP.2015.2411575 10.1109/GlobalSIP.2013.6737048 10.1109/MSP.2017.2717489 10.1364/OL.393213 10.1364/OE.26.001962 10.1109/TIP.2020.2989550 10.1561/9781601984616 10.1109/ISIT.2018.8437878 10.1364/OE.21.010526
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2021.3099035
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Technology Research Database MEDLINE - Academic
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	7111
ExternalDocumentID	10_1109_TPAMI_2021_3099035 9495194
Genre	orig-research
GrantInformation_xml	– fundername: NSFC grantid: 61722110; 61931012; 61631009 – fundername: Beijing Municipal Science & Technology Commission grantid: Z181100003118014
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c328t-980d2ba1f7ca5b4fe84cb84d0fa961c2a44afb154104addd4eab8056bcfa8e783
IEDL.DBID	RIE
ISICitedReferencesCount	72
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000853875300087&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Thu Oct 02 07:08:16 EDT 2025 Sun Nov 09 08:11:06 EST 2025 Sat Nov 29 05:16:00 EST 2025 Tue Nov 18 22:43:54 EST 2025 Wed Aug 27 02:18:57 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	10
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c328t-980d2ba1f7ca5b4fe84cb84d0fa961c2a44afb154104addd4eab8056bcfa8e783
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-7043-3061 0000-0002-5787-0934 0000-0002-3426-1634 0000-0002-8311-7524
PMID	34310288
PQID	2714892903
PQPubID	85458
PageCount	19
ParticipantIDs	proquest_journals_2714892903 crossref_citationtrail_10_1109_TPAMI_2021_3099035 ieee_primary_9495194 proquest_miscellaneous_2555638985 crossref_primary_10_1109_TPAMI_2021_3099035
PublicationCentury	2000
PublicationDate	2022-10-01
PublicationDateYYYYMMDD	2022-10-01
PublicationDate_xml	– month: 10 year: 2022 text: 2022-10-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationYear	2022
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref11 ref55 ref10 ref54 ref17 Ryu (ref48) ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 Y. (ref27) ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref71 ref70 ref72 ref24 ref68 ref23 ref67 ref26 ref25 ref69 ref20 ref63 ref22 Yuan (ref64) 2020 ref66 ref21 ref65 Zhang (ref52) 2018; 27 ref28 ref29 ref60 ref62 ref61
References_xml	– ident: ref17 doi: 10.1364/OE.25.018182 – ident: ref30 doi: 10.1109/TPAMI.2018.2817496 – ident: ref18 doi: 10.1364/OL.386238 – ident: ref62 doi: 10.1137/080716542 – ident: ref56 doi: 10.1137/17M1122451 – ident: ref10 doi: 10.1109/ICCV.2011.6126254 – ident: ref8 doi: 10.1109/CVPR.2014.424 – ident: ref47 doi: 10.1109/TCI.2016.2629286 – ident: ref60 doi: 10.1109/TIP.2006.884928 – ident: ref57 doi: 10.1117/12.766768 – ident: ref23 doi: 10.1109/ICIP.2016.7532817 – ident: ref68 doi: 10.1109/TSP.2006.881199 – ident: ref54 doi: 10.1109/MSP.2007.914730 – ident: ref9 doi: 10.1364/OE.17.006368 – ident: ref42 doi: 10.1007/978-3-030-01249-6_39 – ident: ref66 doi: 10.1145/2487575.2487586 – ident: ref70 doi: 10.1109/TIP.2007.901238 – ident: ref11 doi: 10.1109/CVPR.2011.5995542 – ident: ref40 doi: 10.1109/TIP.2017.2713099 – ident: ref2 doi: 10.1364/AOP.10.000409 – ident: ref16 doi: 10.1063/1.5140721 – start-page: 1 volume-title: Proc. IEEE Int. Conf. Comput. Photogr. ident: ref27 article-title: End-to-end video compressive sensing using anderson-accelerated unrolled networks – ident: ref5 doi: 10.1364/OL.40.004054 – ident: ref44 doi: 10.1109/CVPR46437.2021.01595 – ident: ref12 doi: 10.1364/BOE.7.000746 – ident: ref63 doi: 10.1364/PRJ.411745 – ident: ref65 doi: 10.1109/TIP.2020.3005515 – ident: ref72 doi: 10.1109/TIP.2003.819861 – ident: ref13 doi: 10.1109/TPAMI.2019.2946567 – ident: ref51 doi: 10.1109/TIT.2019.2940666 – ident: ref6 doi: 10.1109/MSP.2020.3023869 – ident: ref1 doi: 10.1126/science.aat2298 – ident: ref32 doi: 10.1007/978-3-030-58592-1_12 – ident: ref3 doi: 10.1364/OPTICA.5.000127 – year: 2020 ident: ref64 article-title: Various total variation for snapshot video compressive imaging – ident: ref33 doi: 10.1364/OPTICA.2.000822 – ident: ref50 doi: 10.1109/CVPR42600.2020.00152 – ident: ref28 doi: 10.1007/978-3-030-58586-0_16 – ident: ref61 doi: 10.1109/TIP.2020.2972109 – ident: ref4 doi: 10.1364/AOP.7.000756 – ident: ref34 doi: 10.1364/AO.55.007556 – ident: ref20 doi: 10.1109/TIP.2007.909319 – volume: 27 start-page: 4608 issue: 9 volume-title: IEEE Trans. Image Process. year: 2018 ident: ref52 article-title: FFDNet: Toward a fast and flexible solution for CNN-based image denoising. – ident: ref37 doi: 10.1016/0167-2789(92)90242-f – ident: ref46 doi: 10.1109/TCI.2016.2599778 – ident: ref36 doi: 10.1109/TIT.2006.871582 – ident: ref69 doi: 10.1109/ICCV.2009.5459452 – ident: ref24 doi: 10.1137/130936658 – start-page: 5546 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref48 article-title: Plug-and-play methods provably converge with properly trained denoisers – ident: ref25 doi: 10.1109/TPAMI.2018.2873587 – ident: ref38 doi: 10.1109/CVPR.2014.366 – ident: ref43 doi: 10.1109/CVPR46437.2021.01598 – ident: ref22 doi: 10.1109/TIP.2014.2344294 – ident: ref71 doi: 10.1109/TIP.2012.2199324 – ident: ref14 doi: 10.1109/ICCV.2019.00416 – ident: ref26 doi: 10.1109/ICCV.2019.01032 – ident: ref35 doi: 10.1364/OE.23.011912 – ident: ref59 doi: 10.1109/ICASSP.2004.1326587 – ident: ref21 doi: 10.1109/TIP.2014.2365720 – ident: ref29 doi: 10.1109/ICIP.2013.6738004 – ident: ref19 doi: 10.1364/OL.420139 – ident: ref53 doi: 10.1109/CVPR42600.2020.00143 – ident: ref58 doi: 10.1364/AOP.398263 – ident: ref15 doi: 10.1109/JSTSP.2015.2411575 – ident: ref45 doi: 10.1109/GlobalSIP.2013.6737048 – ident: ref49 doi: 10.1109/MSP.2017.2717489 – ident: ref31 doi: 10.1364/OL.393213 – ident: ref41 doi: 10.1364/OE.26.001962 – ident: ref67 doi: 10.1109/TIP.2020.2989550 – ident: ref39 doi: 10.1561/9781601984616 – ident: ref55 doi: 10.1109/ISIT.2018.8437878 – ident: ref7 doi: 10.1364/OE.21.010526
SSID	ssj0014503
Score	2.6563125
Snippet	We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector)....
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	7093
SubjectTerms	Algorithms Cameras coded aperture coded aperture compressive temporal imaging (CACTI) Color Compressive sensing computational imaging deep learning Frames (data processing) Gray-scale High speed Image coding Image color analysis image processing Image reconstruction Iterative methods Low speed Machine learning Noise reduction Optimization plug-and-play (PnP) algorithms Plugs Sensors Video compression video processing
Title	Plug-and-Play Algorithms for Video Snapshot Compressive Imaging
URI	https://ieeexplore.ieee.org/document/9495194 https://www.proquest.com/docview/2714892903 https://www.proquest.com/docview/2555638985
Volume	44
WOSCitedRecordID	wos000853875300087&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjBt7i-iOBNq900aZOTLKLoQVnwwd5KkqbuwtrKblfw3zvJdouiCN5Km4aSyWS-r8nMB3DMc55ohLpBLLkKGNKvQFun9aJ5Lmgu8Ib2YhPJ_b3o9WR3Dk6bXBhrrT98Zs_cpd_Lz0ozcb_KziWieSTd8zCfJPE0V6vZMWDcqyAjgkEPRxoxS5AJ5fljt3N3i1SQts8itw8UObmaCCMnxlbxLR55gZUfq7IPNder__vINVipISXpTOfAOszZYgNWZ3INpPbeDVj-UntwEy66w8lLoIos6A7VB-kMX8rRoOq_jgnCWPI8yGxJHgr1Nu6XFXGd-QOz75bcvnphoy14ur56vLwJajWFwERUVIEUYUa1aueJUVyz3ApmtGBZmCsZtw1VjKlcI6JCgoaLXsas0gLhkTa5EjYR0TYsFGVhd4DEkU64lkoahQSDUo3mjaXQmWFSiYy3oD0b09TUpcad4sUw9ZQjlKk3SepMktYmacFJ887btNDGn6033cg3LetBb8H-zHRp7YvjlCZI-RAFhlELjprH6EVua0QVtpxgG-4KpQkp-O7vPe_BEnWJD_4Y3z4sVKOJPYBF814NxqNDnJA9cegn5CfIHNo4
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS-QwEB48FU4f9NQ7XH_m4N602k2TbfIkiygu6rJwq_hWkjTVhbWV3a7gf-8k2y2KIvhW2jSUTCbzfU1mPoB_POOxRqgbtCRXAUP6FWjrtF40zwTNBN7QXmwi7nbF3Z3szcFhnQtjrfWHz-yRu_R7-WlhJu5X2bFENI-k-wcscMZoOM3WqvcMGPc6yIhh0MeRSMxSZEJ53O-1rztIBmnzKHI7QZETrIkwdmJ0Fe8ikpdY-bAu-2Bzvvq9z_wFKxWoJO3pLFiDOZuvw-pMsIFU_rsOy2-qD27ASW84uQ9Unga9oXoh7eF9MRqUD49jgkCW3A5SW5D_uXoaPxQlcZ35I7PPlnQevbTRb7g5P-ufXgSVnkJgIirKQIowpVo1s9gorllmBTNasDTMlGw1DVWMqUwjpkKKhsteyqzSAgGSNpkSNhbRH5jPi9xuAmlFOuZaKmkUUgxKNRq4JYVODZNKpLwBzdmYJqYqNu40L4aJJx2hTLxJEmeSpDJJAw7qd56mpTa-bL3hRr5uWQ16A3ZmpksqbxwnNEbShzgwjBrwt36MfuQ2R1Ruiwm24a5UmpCCb33e8z78vOhfXyVXne7lNixRlwbhD_XtwHw5mthdWDTP5WA82vPT8hUlF9yX
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=Plug-and-Play+Algorithms+for+Video+Snapshot+Compressive+Imaging&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Yuan%2C+Xin&rft.au=Liu%2C+Yang&rft.au=Suo%2C+Jinli&rft.au=Durand%2C+Fredo&rft.date=2022-10-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=44&rft.issue=10&rft.spage=7093&rft.epage=7111&rft_id=info:doi/10.1109%2FTPAMI.2021.3099035&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2021_3099035
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon