Convolutional Sparse Coding for Capturing High‐Speed Video Content

Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 36; no. 8; pp. 380 - 389
Main Authors: Serrano, Ana, Garces, Elena, Masia, Belen, Gutierrez, Diego
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.12.2017
Subjects:
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade‐off remains. The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single‐shot high‐speed video, by coding the temporal information in a single frame, and then reconstructing the full video sequence from this single‐coded image and a trained dictionary of image patches. In this paper, we first analyse this approach, and find insights that help improve the quality of the reconstructed videos. We then introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state‐of‐the‐art, patch‐based approach in terms of flexibility and efficiency, due to the convolutional nature of its filter banks. The key idea for CSC high‐speed video acquisition is extending the basic formulation by imposing an additional constraint in the temporal dimension, which enforces sparsity of the first‐order derivatives over time. Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade‐off remains. We introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state‐of‐the‐art, patch‐based approaches in terms of flexibility and efficiency, due to the convolutional nature of its filter banks.
AbstractList Video capture is limited by the trade-off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade-off remains. The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single-shot high-speed video, by coding the temporal information in a single frame, and then reconstructing the full video sequence from this single-coded image and a trained dictionary of image patches. In this paper, we first analyse this approach, and find insights that help improve the quality of the reconstructed videos. We then introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state-of-the-art, patch-based approach in terms of flexibility and efficiency, due to the convolutional nature of its filter banks. The key idea for CSC high-speed video acquisition is extending the basic formulation by imposing an additional constraint in the temporal dimension, which enforces sparsity of the first-order derivatives over time.
Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade‐off remains. The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single‐shot high‐speed video, by coding the temporal information in a single frame, and then reconstructing the full video sequence from this single‐coded image and a trained dictionary of image patches. In this paper, we first analyse this approach, and find insights that help improve the quality of the reconstructed videos. We then introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state‐of‐the‐art, patch‐based approach in terms of flexibility and efficiency, due to the convolutional nature of its filter banks. The key idea for CSC high‐speed video acquisition is extending the basic formulation by imposing an additional constraint in the temporal dimension, which enforces sparsity of the first‐order derivatives over time.
Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade‐off remains. The recent introduction of compressive sensing and sparse reconstruction techniques allows for the capture of single‐shot high‐speed video, by coding the temporal information in a single frame, and then reconstructing the full video sequence from this single‐coded image and a trained dictionary of image patches. In this paper, we first analyse this approach, and find insights that help improve the quality of the reconstructed videos. We then introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state‐of‐the‐art, patch‐based approach in terms of flexibility and efficiency, due to the convolutional nature of its filter banks. The key idea for CSC high‐speed video acquisition is extending the basic formulation by imposing an additional constraint in the temporal dimension, which enforces sparsity of the first‐order derivatives over time. Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution decreases due to bandwidth limitations in the capture system. Achieving both high spatial and temporal resolution is only possible with highly specialized and very expensive hardware, and even then the same basic trade‐off remains. We introduce a novel technique, based on convolutional sparse coding (CSC), and show how it outperforms the state‐of‐the‐art, patch‐based approaches in terms of flexibility and efficiency, due to the convolutional nature of its filter banks.
Author Masia, Belen
Gutierrez, Diego
Garces, Elena
Serrano, Ana
Author_xml – sequence: 1
  givenname: Ana
  surname: Serrano
  fullname: Serrano, Ana
  email: anase@unizar.es
  organization: Dpto. Informatica e Ing. Sistemas. C/ Maria de Luna, 1. Ed. Ada Byron
– sequence: 2
  givenname: Elena
  surname: Garces
  fullname: Garces, Elena
  email: egarces@unizar.es
  organization: Dpto. Informatica e Ing. Sistemas. C/ Maria de Luna, 1. Ed. Ada Byron
– sequence: 3
  givenname: Belen
  surname: Masia
  fullname: Masia, Belen
  email: bmasia@unizar.es
  organization: MPI Informatik
– sequence: 4
  givenname: Diego
  surname: Gutierrez
  fullname: Gutierrez, Diego
  email: diegog@unizar.es
  organization: MPI Informatik
BookMark eNp9kLFOwzAQhi1UJNrCwBtEYmJIa9exE48o0BapEkOB1XJtp7gKcbAdUDcegWfkSXAoExLccne67_91-kdg0NhGA3CO4ATFmsptNUEYFvQIDFFG87SghA3AEKI455CQEzDyfgchzHJKhuC6tM2rrbtgbCPqZN0K53VSWmWabVJZl5SiDZ3rt6XZPn2-f6xbrVXyaJS2kWuCbsIpOK5E7fXZTx-Dh_nNfblMV3eL2_JqlUqMZzRVOdYyI1AokrEKQsKwIqjaECyoYppBRVWB42GDN0ISpYsMwhkRuSyIUIrhMbg4-LbOvnTaB76znYt_e45YjjMyo7SI1OWBks5673TFW2eehdtzBHkfEo8h8e-QIjv9xUoTRB9GcMLU_yneTK33f1vzcjE_KL4AZfB6gw
CitedBy_id crossref_primary_10_1016_j_sysarc_2020_101934
crossref_primary_10_1109_ACCESS_2019_2908968
crossref_primary_10_1016_j_optcom_2023_130010
crossref_primary_10_1109_MCG_2018_021951638
crossref_primary_10_1109_JSTSP_2017_2743683
Cites_doi 10.1364/OE.23.015992
10.1109/TSP.2006.881199
10.1145/2343483.2343487
10.1145/1276377.1276463
10.1016/j.cag.2013.10.003
10.1117/12.928858
10.1111/cgf.12819
10.1109/TPAMI.2013.19
10.1145/1276377.1276464
10.1109/TIT.2005.862083
10.1111/cgf.12847
10.1111/j.1467-8659.2012.03067.x
10.1145/2661229.2661262
10.1145/2661229.2661260
10.1364/OL.39.003177
10.1145/2461912.2461914
10.1214/009053604000000067
10.1111/j.1467-8659.2011.02073.x
10.1109/TIT.2006.871582
10.1145/1141911.1141957
10.1109/TMI.2010.2090538
ContentType Journal Article
Copyright 2017 The Authors Computer Graphics Forum © 2017 The Eurographics Association and John Wiley & Sons Ltd.
2017 The Eurographics Association and John Wiley & Sons Ltd.
Copyright_xml – notice: 2017 The Authors Computer Graphics Forum © 2017 The Eurographics Association and John Wiley & Sons Ltd.
– notice: 2017 The Eurographics Association and John Wiley & Sons Ltd.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1111/cgf.13086
DatabaseName CrossRef
Computer and Information Systems 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
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
CrossRef

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1467-8659
EndPage 389
ExternalDocumentID 10_1111_cgf_13086
CGF13086
Genre article
GrantInformation_xml – fundername: Gobierno de Aragon
– fundername: Max Planck Center
– fundername: FPI
– fundername: BBVA Foundation
– fundername: ERC
– fundername: Ministry of Economy and Competitiveness
– fundername: Google Faculty Research Award
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEUYR
AEYWJ
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHEFC
AHQJS
AIDQK
AIDYY
AIQQE
AITYG
AIURR
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAYXX
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c3326-d73ec450ad549f00593d51fb53a6d9e90d6d83f00b3bac5de840025a7c85add93
IEDL.DBID DRFUL
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000417496200026&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Fri Jul 25 01:42:23 EDT 2025
Tue Nov 18 21:56:39 EST 2025
Sat Nov 29 03:41:14 EST 2025
Sun Sep 21 06:19:00 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 8
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3326-d73ec450ad549f00593d51fb53a6d9e90d6d83f00b3bac5de840025a7c85add93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink http://zaguan.unizar.es/record/62988
PQID 1973452668
PQPubID 30877
PageCount 10
ParticipantIDs proquest_journals_1973452668
crossref_primary_10_1111_cgf_13086
crossref_citationtrail_10_1111_cgf_13086
wiley_primary_10_1111_cgf_13086_CGF13086
PublicationCentury 2000
PublicationDate December 2017
2017-12-00
20171201
PublicationDateYYYYMMDD 2017-12-01
PublicationDate_xml – month: 12
  year: 2017
  text: December 2017
PublicationDecade 2010
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2017
Publisher Blackwell Publishing Ltd
Publisher_xml – name: Blackwell Publishing Ltd
References 2010; 11
2006; 52
2012
2011
2012; 8499
2006; 54
2010
2009
2011; 30
2007
2006
2000; 1
2004; 2
2003
2016; 35
2012; 31
2004; 32
2015; 23
2013; 37
2013; 36
2013; 32
2013; 35
2006; 25
2015
2014
2013
2014; 39
2014; 33
2007; 26
Koller R. (e_1_2_10_19_1) 2015; 23
Mairal J. (e_1_2_10_23_1) 2010; 11
e_1_2_10_22_1
Almeida M. S. C. (e_1_2_10_3_1) 2013
Masia B. (e_1_2_10_24_1) 2011
Hitomi Y. (e_1_2_10_14_1) 2011
Schöberl M. (e_1_2_10_31_1) 2012; 8499
Veeraraghavan A. (e_1_2_10_35_1) 2007; 26
e_1_2_10_2_1
Wakin M. (e_1_2_10_38_1) 2006
e_1_2_10_6_1
e_1_2_10_39_1
e_1_2_10_5_1
e_1_2_10_17_1
e_1_2_10_8_1
e_1_2_10_7_1
e_1_2_10_36_1
e_1_2_10_9_1
e_1_2_10_13_1
Liu D. (e_1_2_10_21_1) 2013; 36
e_1_2_10_34_1
e_1_2_10_33_1
Heide F. (e_1_2_10_16_1) 2014; 33
e_1_2_10_30_1
Gu J. (e_1_2_10_11_1) 2010
Kong B. (e_1_2_10_18_1) 2014
Wang Z. (e_1_2_10_40_1) 2003
Levin A. (e_1_2_10_20_1) 2007; 26
Grosse R. B. (e_1_2_10_12_1) 2007
Nayar S. (e_1_2_10_28_1) 2000; 1
Zhou C. (e_1_2_10_41_1) 2009
Serrano A. (e_1_2_10_32_1) 2015
Bristow H. (e_1_2_10_4_1) 2013
e_1_2_10_29_1
Gupta A. (e_1_2_10_10_1) 2009
e_1_2_10_27_1
Heide F. (e_1_2_10_15_1) 2015
e_1_2_10_25_1
e_1_2_10_26_1
Wilburn B. (e_1_2_10_37_1) 2004; 2
References_xml – volume: 26
  issue: 3
  year: 2007
  article-title: Dappled photography: Mask enhanced cameras for heterodyned light fields and coded aperture refocusing
  publication-title: ACM Transactions on Graphics
– volume: 35
  start-page: 1887
  issue: 8
  year: 2013
  end-page: 1901
  article-title: Deep learning with hierarchical convolutional factor analysis
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 30
  start-page: 1028
  year: 2011
  end-page: 1041
  article-title: MR image reconstruction from highly undersampled k‐space data by dictionary learning
  publication-title: IEEE Transactions on Medical Imaging
– year: 2006
  article-title: Compressive imaging for video representation and coding
  publication-title: Proceedings of the Picture Coding Symposium
– volume: 52
  start-page: 1289
  year: 2006
  end-page: 1306
  article-title: Compressed sensing
  publication-title: IEEE Transactions on Information Theory
– volume: 31
  start-page: 1867
  year: 2012
  end-page: 1879
  article-title: Perceptually optimized coded apertures for defocus deblurring
  publication-title: Computer Graphics Forum
– volume: 1
  start-page: 472
  year: 2000
  end-page: 479
  article-title: High dynamic range imaging: Spatially varying pixel exposures
  publication-title: Proceedins of CVPR
– year: 2009
  article-title: Enhancing and experiencing spacetime resolution with videos and stills
  publication-title: Proceedings of the IEEE International Conference on Computational Photography
– start-page: 582
  year: 2013
  end-page: 585
  article-title: Frame‐based image deblurring with unknown boundary conditions using the alternating direction method of multipliers
  publication-title: Proceedings of the IEEE ICIP
– year: 2011
  article-title: Coded apertures for defocus blurring
  publication-title: Proceedings of Ibero‐American Symposium in Computer Graphics
– volume: 32
  start-page: 1
  year: 2013
  end-page: 11
  article-title: Compressive light field photography using overcomplete dictionaries and optimized projections
  publication-title: ACM Transactions on Graphics
– volume: 8499
  start-page: 84990C
  year: 2012
  end-page: 84990C‐11
  article-title: Building a high dynamic range video sensor with spatially nonregular optical filtering
  publication-title: Proceedings of SPIE
– volume: 39
  start-page: 3177
  issue: 11
  year: 2014
  end-page: 3180
  article-title: Robust and accurate transient light transport decomposition via convolutional sparse coding
  publication-title: Optics Letters
– start-page: 1398
  year: 2003
  end-page: 1402
  article-title: multi‐scale structural similarity for image quality assessment
  publication-title: Proceedings of IEEE Conf. on Signals, Systems and Computers
– volume: 11
  start-page: 16
  year: 2010
  end-page: 60
  article-title: Online learning for matrix factorization and sparse coding
  publication-title: Journal of Machine Learning Research
– year: 2014
– start-page: 391
  year: 2013
  end-page: 398
  article-title: Fast convolutional sparse coding
  publication-title: Proceedings of CVPR
– start-page: 149
  year: 2007
  end-page: 158
  article-title: Shift‐invariant sparse coding for audio classification
  publication-title: Proceedings of UAI
– year: 2010
– year: 2012
– year: 2015
  article-title: Compressive high speed video acquisition
  publication-title: Proceedings of CEIG
– volume: 37
  start-page: 1012
  issue: 8
  year: 2013
  end-page: 1038
  article-title: A survey on computational displays: Pushing the boundaries of optics, computation, and perception
  publication-title: Computers & Graphics
– start-page: 287
  year: 2011
  end-page: 294
  article-title: Video from a single coded exposure photograph using a learned over‐complete dictionary
  publication-title: Proceedings of the IEEE International Conference on Computer Vision (ICCV)
– volume: 25
  start-page: 795
  year: 2006
  end-page: 804
  article-title: Coded exposure photography: Motion deblurring using fluttered shutter
  publication-title: ACM Transactions on Graphics
– volume: 52
  start-page: 489
  year: 2006
  end-page: 509
  article-title: Robust incertainty principles: Exact signal reconstruction from highly incomplete frequency information
  publication-title: IEEE Transactions on Information Theory
– volume: 2
  start-page: 294
  year: 2004
  end-page: 301
  article-title: High‐speed videography using a dense camera array
  publication-title: Computer Vision and Pattern Recognition
– volume: 30
  start-page: 2397
  issue: 8
  year: 2011
  end-page: 2426
  article-title: Computational plenoptic imaging
  publication-title: Computer Graphics Forum
– volume: 35
  start-page: 153
  issue: 2
  year: 2016
  end-page: 163
  article-title: Convolutional sparse coding for high dynamic range imaging
  publication-title: Computer Graphics Forum
– volume: 35
  start-page: 467
  issue: 2
  year: 2016
  end-page: 477
  article-title: Multisampling compressive video spectroscopy
  publication-title: Computer Graphics Forum
– volume: 23
  start-page: 15992
  issue: 12
  year: 2015
  end-page: 16007
  article-title: High spatio‐temporal resolution video with compressed sensing
  publication-title: Optics Express
– start-page: 325
  year: 2009
  end-page: 332
  article-title: Coded aperture pairs for depth from defocus
  publication-title: Proceedings of IEEE International Conference on Computer Vision (ICCV)
– volume: 36
  start-page: 248
  year: 2013
  end-page: 260
  article-title: Efficient space‐time sampling with pixel‐wise coded exposure for high speed imaging
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– year: 2010
  article-title: Coded rolling shutter photography: Flexible space‐time sampling
  publication-title: Proceedings of IEEE International Conference on Computational Photography
– year: 2015
  article-title: Fast and flexible convolutional sparse coding
  publication-title: Proceedings of CVPR
– volume: 26
  year: 2007
  article-title: Image and depth from a conventional camera with a coded aperture
  publication-title: ACM Transactions on Graphics
– volume: 33
  start-page: 231:1
  issue: 6
  year: 2014
  end-page: 231:13
  article-title: FlexISP: A flexible camera image processing framework
  publication-title: ACM Transactions on Graphics
– volume: 54
  start-page: 4311
  year: 2006
  end-page: 4322
  article-title: K‐SVD: An algorithm for designing overcomplete dictionaries for sparse representation
  publication-title: IEEE Transactions on Signal Processing
– volume: 32
  start-page: 407
  year: 2004
  end-page: 499
  article-title: Least angle regression
  publication-title: Annals of Statistics
– volume: 33
  start-page: 1
  year: 2014
  end-page: 11
  article-title: Spatial‐spectral encoded compressive hyperspectral imaging
  publication-title: ACM Transactions on Graphics
– ident: e_1_2_10_5_1
– volume: 23
  start-page: 15992
  issue: 12
  year: 2015
  ident: e_1_2_10_19_1
  article-title: High spatio‐temporal resolution video with compressed sensing
  publication-title: Optics Express
  doi: 10.1364/OE.23.015992
– ident: e_1_2_10_2_1
  doi: 10.1109/TSP.2006.881199
– ident: e_1_2_10_39_1
  doi: 10.1145/2343483.2343487
– start-page: 391
  year: 2013
  ident: e_1_2_10_4_1
  article-title: Fast convolutional sparse coding
  publication-title: Proceedings of CVPR
– volume: 26
  issue: 3
  year: 2007
  ident: e_1_2_10_35_1
  article-title: Dappled photography: Mask enhanced cameras for heterodyned light fields and coded aperture refocusing
  publication-title: ACM Transactions on Graphics
  doi: 10.1145/1276377.1276463
– start-page: 1398
  year: 2003
  ident: e_1_2_10_40_1
  article-title: multi‐scale structural similarity for image quality assessment
  publication-title: Proceedings of IEEE Conf. on Signals, Systems and Computers
– ident: e_1_2_10_27_1
  doi: 10.1016/j.cag.2013.10.003
– volume: 1
  start-page: 472
  year: 2000
  ident: e_1_2_10_28_1
  article-title: High dynamic range imaging: Spatially varying pixel exposures
  publication-title: Proceedins of CVPR
– year: 2009
  ident: e_1_2_10_10_1
  article-title: Enhancing and experiencing spacetime resolution with videos and stills
  publication-title: Proceedings of the IEEE International Conference on Computational Photography
– volume: 8499
  start-page: 84990C
  year: 2012
  ident: e_1_2_10_31_1
  article-title: Building a high dynamic range video sensor with spatially nonregular optical filtering
  publication-title: Proceedings of SPIE
  doi: 10.1117/12.928858
– ident: e_1_2_10_33_1
  doi: 10.1111/cgf.12819
– ident: e_1_2_10_6_1
  doi: 10.1109/TPAMI.2013.19
– year: 2006
  ident: e_1_2_10_38_1
  article-title: Compressive imaging for video representation and coding
  publication-title: Proceedings of the Picture Coding Symposium
– volume: 26
  year: 2007
  ident: e_1_2_10_20_1
  article-title: Image and depth from a conventional camera with a coded aperture
  publication-title: ACM Transactions on Graphics
  doi: 10.1145/1276377.1276464
– year: 2011
  ident: e_1_2_10_24_1
  article-title: Coded apertures for defocus blurring
  publication-title: Proceedings of Ibero‐American Symposium in Computer Graphics
– ident: e_1_2_10_7_1
  doi: 10.1109/TIT.2005.862083
– volume: 36
  start-page: 248
  year: 2013
  ident: e_1_2_10_21_1
  article-title: Efficient space‐time sampling with pixel‐wise coded exposure for high speed imaging
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– year: 2010
  ident: e_1_2_10_11_1
  article-title: Coded rolling shutter photography: Flexible space‐time sampling
  publication-title: Proceedings of IEEE International Conference on Computational Photography
– ident: e_1_2_10_17_1
  doi: 10.1111/cgf.12847
– ident: e_1_2_10_25_1
  doi: 10.1111/j.1467-8659.2012.03067.x
– year: 2015
  ident: e_1_2_10_32_1
  article-title: Compressive high speed video acquisition
  publication-title: Proceedings of CEIG
– ident: e_1_2_10_22_1
  doi: 10.1145/2661229.2661262
– ident: e_1_2_10_34_1
– volume: 33
  start-page: 231:1
  issue: 6
  year: 2014
  ident: e_1_2_10_16_1
  article-title: FlexISP: A flexible camera image processing framework
  publication-title: ACM Transactions on Graphics
  doi: 10.1145/2661229.2661260
– ident: e_1_2_10_13_1
  doi: 10.1364/OL.39.003177
– ident: e_1_2_10_26_1
  doi: 10.1145/2461912.2461914
– year: 2015
  ident: e_1_2_10_15_1
  article-title: Fast and flexible convolutional sparse coding
  publication-title: Proceedings of CVPR
– ident: e_1_2_10_9_1
  doi: 10.1214/009053604000000067
– volume: 11
  start-page: 16
  year: 2010
  ident: e_1_2_10_23_1
  article-title: Online learning for matrix factorization and sparse coding
  publication-title: Journal of Machine Learning Research
– ident: e_1_2_10_36_1
  doi: 10.1111/j.1467-8659.2011.02073.x
– start-page: 287
  year: 2011
  ident: e_1_2_10_14_1
  article-title: Video from a single coded exposure photograph using a learned over‐complete dictionary
  publication-title: Proceedings of the IEEE International Conference on Computer Vision (ICCV)
– ident: e_1_2_10_8_1
  doi: 10.1109/TIT.2006.871582
– volume-title: Fast Convolutional Sparse Coding (FCSC)
  year: 2014
  ident: e_1_2_10_18_1
– ident: e_1_2_10_29_1
  doi: 10.1145/1141911.1141957
– start-page: 149
  year: 2007
  ident: e_1_2_10_12_1
  article-title: Shift‐invariant sparse coding for audio classification
  publication-title: Proceedings of UAI
– ident: e_1_2_10_30_1
  doi: 10.1109/TMI.2010.2090538
– start-page: 582
  year: 2013
  ident: e_1_2_10_3_1
  article-title: Frame‐based image deblurring with unknown boundary conditions using the alternating direction method of multipliers
  publication-title: Proceedings of the IEEE ICIP
– volume: 2
  start-page: 294
  year: 2004
  ident: e_1_2_10_37_1
  article-title: High‐speed videography using a dense camera array
  publication-title: Computer Vision and Pattern Recognition
– start-page: 325
  year: 2009
  ident: e_1_2_10_41_1
  article-title: Coded aperture pairs for depth from defocus
  publication-title: Proceedings of IEEE International Conference on Computer Vision (ICCV)
SSID ssj0004765
Score 2.2363446
Snippet Video capture is limited by the trade‐off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution...
Video capture is limited by the trade-off between spatial and temporal resolution: when capturing videos of high temporal resolution, the spatial resolution...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 380
SubjectTerms computational photography
Filter banks
High speed
I.4.1 [Computer Graphics]: Digitization and Image Capture
Image reconstruction
Sampling
Spatial resolution
Temporal resolution
Tradeoffs
Title Convolutional Sparse Coding for Capturing High‐Speed Video Content
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.13086
https://www.proquest.com/docview/1973452668
Volume 36
WOSCitedRecordID wos000417496200026&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NSsNAEB5q60EP_ovVKkE8eAm03exuFk-SWj2UItaW3sJmdyMFSUIbe_YRfEafxN1t0lZQELwFMvlhdmbnm2XmG4ArIblhHdfIjcXE9aJ27HLFuEsM3VrMkKfsrMNRj_b7_njMHitwU_bCLPghlgduxjPsfm0cnEezNScXL7EZZeyTDaiZpipchVrnqTvsrdoiKcEltbchjSmIhUwhz_Lh7-FohTHXkaoNNd3df_3kHuwUCNO5XZjEPlRUcgDba7yDh9AJ0mRe2JwWHWQ6u1VOkJo45mgU6wQ8y23_omPqQD7fPwaZjnLOaCJV6lhCqyQ_gmH37jl4cItxCq5AGqS5kiIlPNzkUueEsZ3lJ3ErjjDiRDLFmpJIH-kbEYq4wFLp3E-rlVPhY70LMnQM1SRN1Ak4HMmYCkJ8hblHlWQ8bkaUUNLiSBAh63BdajUUBde4GXnxGpY5h1ZMaBVTh8ulaLYg2PhJqFEuTVj42CxsMYrMgHTi68_ZRfj9BWFw37UXp38XPYOttonhtnalAdV8-qbOYVPM88lselEY2xcN4tfR
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qK6gH32K1ahAPXgJtN9nNghdJrRVjEfvAW9jsbqQgSWlrz_4Ef6O_xN1t0lZQELwFMnkwO7PzzTLzDcAFF0yzjivkRmNsO1E9tpmkzMaabi2myJFm1mE_IO229_xMHwtwlffCzPgh5gdu2jPMfq0dXB9IL3k5f4n1LGMPr0DJwcpRilBqPDV7waIvkmA35_bWrDEZs5Cu5Jk__D0eLUDmMlQ1saa59b-_3IbNDGNa1zOj2IGCTHZhY4l5cA8afppMM6tTop2hym-l5ac6klkKx1o-G05MB6OlK0E-3z86QxXnrP5AyNQylFbJZB96zZuu37KzgQo2Rwqm2YIgyR23yoTKCmMzzU-4tThyEcOCSloVWHhI3YhQxLgrpMr-FCZihHuu2gcpOoBikibyECyGREw4xp50mUOkoCyuRgQTXGOIYy7KcJmrNeQZ27geevEa5lmHUkxoFFOG87nocEax8ZNQJV-bMPOycVijBOkR6dhTnzOr8PsLQv-2aS6O_i56Bmut7kMQBnft-2NYr-uIbipZKlCcjN7kCazy6WQwHp1mlvcFAP_bwQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qFdGDb7E-g3jwEmi72d0seJHUqFiKqC29hc0-pCBp0NqzP8Hf6C9xd5vUCgqCt0AmD2Zndr5ZZr4BOBGSW9Zxg9yYJn6QNrXPFeM-sXRrmqFAuVmHvTbtdMJ-n91W4KzshZnwQ0wP3KxnuP3aOrjKpZ7xcvGo7SzjkMzBfIAZblZhvnUXd9tffZGU4JLb27LGFMxCtpJn-vD3ePQFMmehqos18er__nINVgqM6Z1PjGIdKirbgOUZ5sFNaEXDbFxYnRG9z01-q7xoaCOZZ3CsF_F85DoYPVsJ8vH2fp-bOOf1BlINPUdplY22oBtfPERXfjFQwRfIwDRfUqREgOtcmqxQu2l-Ejd0ihEnkilWl0SGyNxIUcoFlspkfwYTcSpCbPZBhrahmg0ztQMeR1JTQUioMA-okozrekoJJQ2OBBGyBqelWhNRsI3boRdPSZl1GMUkTjE1OJ6K5hOKjZ-E9su1SQove0kajCI7Ip2E5nNuFX5_QRJdxu5i9--iR7B424qT9nXnZg-Wmjagu0KWfaiOnl_VASyI8Wjw8nxYGN4nwXDbPA
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=Convolutional+Sparse+Coding+for+Capturing+High-Speed+Video+Content&rft.jtitle=Computer+graphics+forum&rft.au=Serrano%2C+Ana&rft.au=Garces%2C+Elena&rft.au=Masia%2C+Belen&rft.au=Gutierrez%2C+Diego&rft.date=2017-12-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=36&rft.issue=8&rft.spage=380&rft_id=info:doi/10.1111%2Fcgf.13086&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon