Deblurring Images via Dark Channel Prior

We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 40; číslo 10; s. 2315 - 2328
Hlavní autoři:	Pan, Jinshan, Sun, Deqing, Pfister, Hanspeter, Yang, Ming-Hsuan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.10.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithm design and analysis Algorithms Convolution dark channel prior Face Image deblurring Image edge detection Image restoration Kernel linear approximation non-uniform deblurring Optimization Pixels Sparsity
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing.
AbstractList	We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing. We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing.We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the dark channel of blurred images is less sparse. While most patches in a clean image contain some dark pixels, this is not the case when they are averaged with neighboring ones by motion blur. This change in sparsity of the dark channel pixels is an inherent property of the motion blur process, which we prove mathematically and validate using image data. Enforcing sparsity of the dark channel thus helps blind deblurring in various scenarios such as natural, face, text, and low-illumination images. However, imposing sparsity of the dark channel introduces a non-convex non-linear optimization problem. In this work, we introduce a linear approximation to address this issue. Extensive experiments demonstrate that the proposed deblurring algorithm achieves the state-of-the-art results on natural images and performs favorably against methods designed for specific scenarios. In addition, we show that the proposed method can be applied to image dehazing.
Author	Pan, Jinshan Pfister, Hanspeter Yang, Ming-Hsuan Sun, Deqing
Author_xml	– sequence: 1 givenname: Jinshan orcidid: 0000-0003-0304-9507 surname: Pan fullname: Pan, Jinshan email: sdluran@gmail.com organization: Nanjing University of Science and Technology, Nanjing, China – sequence: 2 givenname: Deqing surname: Sun fullname: Sun, Deqing email: deqings@nvidia.com organization: NVIDIA, Westford, MA – sequence: 3 givenname: Hanspeter surname: Pfister fullname: Pfister, Hanspeter email: pfister@seas.harvard.edu organization: Harvard University, Cambridge, MA – sequence: 4 givenname: Ming-Hsuan orcidid: 0000-0003-4848-2304 surname: Yang fullname: Yang, Ming-Hsuan email: mhyang@ucmerced.edu organization: University of California, Merced, CA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/28952935$$D View this record in MEDLINE/PubMed
BookMark	eNp9kLtOxDAQAC0EguPxAyChSDQ0ObxrO4lLdLxOAkEBteU4GzDkErATJP6ewB0UFFQudmbXmm223nYtMbYPfArA9cn93enNfIoc8inmShRcrrEJQsZTjRrX2YRDhmlRYLHFtmN85hyk4mKTbWGhFWqhJuz4jMpmCMG3j8l8YR8pJu_eJmc2vCSzJ9u21CR3wXdhl23Utom0t3p32MPF-f3sKr2-vZzPTq9TJxT0qSZpLc9VWeVIdV6j4rbOKlcXZDMHtbTSCpIVQekk8FKV6CAn1NI5rLASO-x4ufc1dG8Dxd4sfHTUNLalbogGtBSZEgLUiB79QZ-7IbTj7wwC5GMILvVIHa6ooVxQZV6DX9jwYX4ajAAuARe6GAPVvwhw8xXafIc2X6HNKvQoFX8k53vb-67tg_XN_-rBUvVE9HtrnBRKCvEJlmSI8Q
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1109_TCSVT_2023_3250509 crossref_primary_10_3390_app10030939 crossref_primary_10_1109_LSP_2022_3212641 crossref_primary_10_1007_s10489_023_05122_1 crossref_primary_10_1007_s11263_018_01146_0 crossref_primary_10_3390_s21103484 crossref_primary_10_1007_s11042_023_14335_y crossref_primary_10_1016_j_dsp_2023_103912 crossref_primary_10_1109_TIP_2020_2980173 crossref_primary_10_1007_s13042_023_01984_6 crossref_primary_10_1109_ACCESS_2019_2956947 crossref_primary_10_1007_s00371_019_01762_y crossref_primary_10_3390_jmse9060570 crossref_primary_10_1109_TIP_2021_3076367 crossref_primary_10_1007_s11760_024_03657_5 crossref_primary_10_1007_s00371_024_03632_8 crossref_primary_10_1016_j_cviu_2020_103100 crossref_primary_10_1109_ACCESS_2022_3226812 crossref_primary_10_1109_TPAMI_2020_3036667 crossref_primary_10_1109_TPAMI_2021_3063604 crossref_primary_10_1038_s41598_024_60157_9 crossref_primary_10_1007_s11760_021_01977_4 crossref_primary_10_1016_j_neunet_2023_08_010 crossref_primary_10_3390_info14050296 crossref_primary_10_3390_s21082625 crossref_primary_10_1016_j_dsp_2021_103008 crossref_primary_10_1109_ACCESS_2020_3045857 crossref_primary_10_1109_JOE_2024_3463840 crossref_primary_10_1016_j_patcog_2022_108988 crossref_primary_10_3390_e24101414 crossref_primary_10_1007_s11760_023_02888_2 crossref_primary_10_1016_j_sysarc_2022_102584 crossref_primary_10_1109_TCDS_2022_3157766 crossref_primary_10_1016_j_asoc_2020_106296 crossref_primary_10_1016_j_ipm_2021_102675 crossref_primary_10_1007_s11760_021_01929_y crossref_primary_10_1364_PRJ_488310 crossref_primary_10_1109_TPAMI_2021_3115139 crossref_primary_10_1007_s00034_024_02865_1 crossref_primary_10_1109_TCSVT_2022_3190516 crossref_primary_10_1109_TIP_2020_3016134 crossref_primary_10_1109_TIP_2024_3442613 crossref_primary_10_1109_TIP_2023_3328486 crossref_primary_10_1016_j_ins_2022_05_033 crossref_primary_10_1109_TPAMI_2021_3138787 crossref_primary_10_3390_s22062168 crossref_primary_10_1016_j_jvcir_2022_103717 crossref_primary_10_1109_TCSVT_2023_3270173 crossref_primary_10_1109_TGRS_2020_2987400 crossref_primary_10_1109_TIP_2024_3425169 crossref_primary_10_1016_j_sigpro_2019_107453 crossref_primary_10_1109_ACCESS_2021_3067055 crossref_primary_10_1109_TIP_2020_3016490 crossref_primary_10_1016_j_optlaseng_2025_109235 crossref_primary_10_1016_j_neucom_2020_01_004 crossref_primary_10_1109_TCSVT_2025_3541429 crossref_primary_10_1007_s11263_023_01957_w crossref_primary_10_1007_s12206_022_0640_6 crossref_primary_10_1109_TIP_2024_3364529 crossref_primary_10_1049_ipr2_12362 crossref_primary_10_1109_TGRS_2019_2935150 crossref_primary_10_1109_TPAMI_2023_3243059 crossref_primary_10_3390_s24206545 crossref_primary_10_1109_TCI_2020_2964202 crossref_primary_10_1109_TIP_2021_3073856 crossref_primary_10_1007_s13369_023_07986_4 crossref_primary_10_1016_j_media_2024_103319 crossref_primary_10_1117_1_JEI_32_6_063022 crossref_primary_10_1007_s11042_020_09012_3 crossref_primary_10_1016_j_dsp_2019_01_004 crossref_primary_10_1364_AO_510746 crossref_primary_10_1016_j_optcom_2022_128961 crossref_primary_10_1007_s00521_024_09495_3 crossref_primary_10_1007_s00034_025_03106_9 crossref_primary_10_1016_j_patcog_2020_107597 crossref_primary_10_1007_s11760_025_04294_2 crossref_primary_10_1007_s00371_023_03014_6 crossref_primary_10_1016_j_autcon_2024_105727 crossref_primary_10_1016_j_inffus_2024_102857 crossref_primary_10_3390_s22166216 crossref_primary_10_1109_ACCESS_2021_3112491 crossref_primary_10_1109_TGRS_2022_3202867 crossref_primary_10_1016_j_patcog_2025_112358 crossref_primary_10_1109_TPAMI_2021_3116135 crossref_primary_10_1109_TIE_2024_3447752 crossref_primary_10_1109_TIP_2023_3280358 crossref_primary_10_1016_j_dsp_2023_103953 crossref_primary_10_1016_j_jvcir_2020_102921 crossref_primary_10_1088_1742_6596_1627_1_012017 crossref_primary_10_3390_s25165211 crossref_primary_10_1109_TIP_2022_3216216 crossref_primary_10_1109_TNNLS_2022_3151099 crossref_primary_10_3390_electronics10172045 crossref_primary_10_1007_s11063_019_10123_8 crossref_primary_10_1109_TPAMI_2019_2920591 crossref_primary_10_3390_s21103317 crossref_primary_10_1007_s13042_022_01659_8 crossref_primary_10_1007_s11042_020_09762_0 crossref_primary_10_1002_cav_2066 crossref_primary_10_1109_TIP_2021_3092814 crossref_primary_10_1016_j_jvcir_2025_104388 crossref_primary_10_1364_AO_571832 crossref_primary_10_1109_TCI_2023_3323835 crossref_primary_10_1007_s11801_021_0081_y crossref_primary_10_1109_TMM_2021_3090206 crossref_primary_10_1016_j_knosys_2020_106617 crossref_primary_10_1109_JSTARS_2023_3269784 crossref_primary_10_1145_3735649 crossref_primary_10_1016_j_knosys_2024_112138 crossref_primary_10_1007_s11042_020_10232_w crossref_primary_10_1007_s10851_020_00949_6 crossref_primary_10_3390_math10081238 crossref_primary_10_1109_ACCESS_2021_3120058 crossref_primary_10_1109_TCSVT_2023_3319330 crossref_primary_10_1016_j_cosrev_2024_100669 crossref_primary_10_1016_j_autcon_2022_104595 crossref_primary_10_1109_ACCESS_2021_3116194 crossref_primary_10_1109_ACCESS_2020_3007972 crossref_primary_10_1007_s00034_023_02327_0 crossref_primary_10_1109_TMM_2022_3152090 crossref_primary_10_1109_TNNLS_2023_3340730 crossref_primary_10_1007_s11045_022_00863_7 crossref_primary_10_1109_TCSVT_2024_3385468 crossref_primary_10_1007_s11263_023_01833_7 crossref_primary_10_1109_TIM_2022_3230482 crossref_primary_10_1016_j_patcog_2020_107300 crossref_primary_10_1109_TCI_2024_3377132 crossref_primary_10_1016_j_neucom_2019_11_063 crossref_primary_10_1109_TCI_2021_3100998 crossref_primary_10_1016_j_patrec_2021_12_009 crossref_primary_10_1109_TCSVT_2020_3034137 crossref_primary_10_1007_s11801_022_1111_0 crossref_primary_10_1016_j_imavis_2024_105080 crossref_primary_10_1109_TGRS_2022_3207828 crossref_primary_10_1016_j_displa_2024_102860 crossref_primary_10_1049_itr2_12269 crossref_primary_10_1109_TPAMI_2021_3102575 crossref_primary_10_3390_electronics11142177 crossref_primary_10_1007_s00138_021_01201_w crossref_primary_10_1088_1361_6420_acc2e0 crossref_primary_10_1007_s11801_025_3275_x crossref_primary_10_1016_j_optlaseng_2024_108431 crossref_primary_10_1016_j_eswa_2023_123005 crossref_primary_10_1007_s11263_022_01583_y crossref_primary_10_1109_TPAMI_2022_3226276 crossref_primary_10_1016_j_patcog_2023_109719 crossref_primary_10_1049_ipr2_12832
Cites_doi	10.1109/ICCV.2011.6126276 10.1145/1360612.1360672 10.1109/CVPR.2016.180 10.1017/CBO9781107360181.002 10.1007/s11263-015-0857-2 10.1109/TPAMI.2015.2481418 10.1109/TPAMI.2010.222 10.1109/TPAMI.2016.2551244 10.1109/CVPR.2011.5995568 10.1109/CVPR.2015.7298677 10.1109/CVPR.2014.372 10.1086/111605 10.1007/978-3-642-33715-4_38 10.1109/CVPR.2011.5995521 10.1109/CVPR.2011.5995308 10.1109/CVPR.2009.5206815 10.1007/978-3-642-15549-9_12 10.1109/ICCV.2007.4408922 10.1109/CVPR.2014.432 10.1137/080724265 10.1109/CVPR.2013.147 10.1109/ICCV.2011.6126280 10.1109/ICCV.2011.6126278 10.1109/83.661187 10.1007/978-3-319-46487-9_45 10.1109/TIP.2011.2164413 10.1145/1661412.1618491 10.1109/ICCV.2001.937655 10.1145/1141911.1141956 10.1109/ICCV.2013.296 10.1007/s10851-010-0220-8 10.1109/CVPR.2008.4587834 10.1109/CVPR.2016.306 10.1109/TIP.2007.918028 10.1007/s11263-011-0502-7 10.1109/TPAMI.2016.2608882 10.1007/978-3-642-33715-4_5
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2017.2753804
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE CrossRef PubMed 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 PubMed 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 PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 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	2328
ExternalDocumentID	28952935 10_1109_TPAMI_2017_2753804 8048543
Genre	orig-research Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: IARPA via DoI/IBC grantid: D16PC00002 – fundername: National Key R&D Program of China grantid: 2016YFB1001001 – fundername: US National Science Foundation grantid: IIS-1447344; IIS-1607800 – fundername: 973 Program of China grantid: 2014CB347600 – fundername: US National Science Foundation CAREER grantid: 1149783 – fundername: NSF of China grantid: 61732007 – fundername: Adobe and Nvidia – fundername: NSF of Jiangsu Province grantid: BK20140058
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 5VS 9M8 AAYOK ABFSI ADRHT AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM PKN RIC RIG RNI RZB VH1 XJT Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c351t-9e4aa075bd72ef7f250af6dcf8ea6c1f4a4a3e4de1bc410b5b2c17e294cc2d2d3
IEDL.DBID	RIE
ISICitedReferencesCount	210
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000443875500003&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	Sun Sep 28 05:13:12 EDT 2025 Mon Dec 01 00:29:25 EST 2025 Wed Feb 19 02:33:54 EST 2025 Tue Nov 18 22:17:44 EST 2025 Sat Nov 29 05:15:58 EST 2025 Wed Aug 27 02:56:05 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-c351t-9e4aa075bd72ef7f250af6dcf8ea6c1f4a4a3e4de1bc410b5b2c17e294cc2d2d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-0304-9507 0000-0003-4848-2304
PMID	28952935
PQID	2117160049
PQPubID	85458
PageCount	14
ParticipantIDs	proquest_miscellaneous_1943653315 proquest_journals_2117160049 crossref_primary_10_1109_TPAMI_2017_2753804 pubmed_primary_28952935 crossref_citationtrail_10_1109_TPAMI_2017_2753804 ieee_primary_8048543
PublicationCentury	2000
PublicationDate	2018-10-01
PublicationDateYYYYMMDD	2018-10-01
PublicationDate_xml	– month: 10 year: 2018 text: 2018-10-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2018
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	ref15 ref14 ref11 ref10 sun (ref18) 2013 gupta (ref38) 2010 ref16 ref19 lemire (ref49) 2006; 13 xu (ref34) 2011; 30 wieschollek (ref31) 2016 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 he (ref32) 2009 ref8 ref9 ref4 ref3 michaeli (ref12) 2014 ref5 ref40 ref35 ref37 ref36 ref30 ref33 ref2 ref1 ref39 zhang (ref24) 2011 shan (ref7) 2008; 27 zoran (ref29) 2016 ref23 ref26 ref25 ref20 ref22 ref21 pan (ref13) 2014 köhler (ref17) 2012 ref28 ref27 chen (ref50) 2016 pan (ref6) 2014
References_xml	– ident: ref39 doi: 10.1109/ICCV.2011.6126276 – volume: 27 year: 2008 ident: ref7 article-title: High-quality motion deblurring from a single image publication-title: ACM SIGGRAPH doi: 10.1145/1360612.1360672 – ident: ref19 doi: 10.1109/CVPR.2016.180 – ident: ref20 doi: 10.1017/CBO9781107360181.002 – ident: ref44 doi: 10.1007/s11263-015-0857-2 – start-page: 221 year: 2016 ident: ref29 article-title: A neural approach to blind motion deblurring publication-title: Proc Eur Conf Comput Vis – ident: ref28 doi: 10.1109/TPAMI.2015.2481418 – ident: ref41 doi: 10.1109/TPAMI.2010.222 – ident: ref37 doi: 10.1109/TPAMI.2016.2551244 – start-page: 171 year: 2010 ident: ref38 article-title: Single image deblurring using motion density functions publication-title: Proc Eur Conf Comput Vis – ident: ref14 doi: 10.1109/CVPR.2011.5995568 – ident: ref30 doi: 10.1109/CVPR.2015.7298677 – start-page: 783 year: 2014 ident: ref12 article-title: Blind deblurring using internal patch recurrence publication-title: Proc Eur Conf Comput Vis – ident: ref25 doi: 10.1109/CVPR.2014.372 – ident: ref1 doi: 10.1086/111605 – start-page: 27 year: 2012 ident: ref17 article-title: Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database publication-title: Proc Eur Conf Comput Vis – ident: ref15 doi: 10.1007/978-3-642-33715-4_38 – ident: ref4 doi: 10.1109/CVPR.2011.5995521 – volume: 13 start-page: 328 year: 2006 ident: ref49 article-title: Streaming maximum-minimum filter using no more than three comparisons per element publication-title: Nordic J Comput – ident: ref5 doi: 10.1109/CVPR.2011.5995308 – ident: ref9 doi: 10.1109/CVPR.2009.5206815 – start-page: 1956 year: 2009 ident: ref32 article-title: Single image haze removal using dark channel prior publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref11 doi: 10.1007/978-3-642-15549-9_12 – ident: ref40 doi: 10.1109/ICCV.2007.4408922 – start-page: 2901 year: 2014 ident: ref6 article-title: Deblurring text images via L $_0$ -regularized intensity and gradient prior publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref16 doi: 10.1109/CVPR.2014.432 – ident: ref36 doi: 10.1137/080724265 – ident: ref8 doi: 10.1109/CVPR.2013.147 – ident: ref47 doi: 10.1109/ICCV.2011.6126280 – ident: ref43 doi: 10.1109/ICCV.2011.6126278 – ident: ref2 doi: 10.1109/83.661187 – ident: ref45 doi: 10.1007/978-3-319-46487-9_45 – ident: ref21 doi: 10.1109/TIP.2011.2164413 – ident: ref10 doi: 10.1145/1661412.1618491 – ident: ref33 doi: 10.1109/ICCV.2001.937655 – ident: ref3 doi: 10.1145/1141911.1141956 – volume: 30 year: 2011 ident: ref34 article-title: Image smoothing via L $_{0}$ gradient minimization publication-title: ACM SIGGRAPH ASIA – ident: ref27 doi: 10.1109/ICCV.2013.296 – start-page: 1 year: 2013 ident: ref18 article-title: Edge-based blur kernel estimation using patch priors publication-title: Proc IEEE Int Conf Comput Photography – ident: ref22 doi: 10.1007/s10851-010-0220-8 – start-page: 35 year: 2016 ident: ref31 article-title: End-to-end learning for image burst deblurring publication-title: Proc Asian Conf Comput Vis – ident: ref26 doi: 10.1109/CVPR.2008.4587834 – ident: ref46 doi: 10.1109/CVPR.2016.306 – start-page: 1 year: 2011 ident: ref24 article-title: Sparse representation based blind image deblurring publication-title: Proc IEEE Int Conf Multimedia Expo – ident: ref23 doi: 10.1109/TIP.2007.918028 – ident: ref42 doi: 10.1007/s11263-011-0502-7 – ident: ref35 doi: 10.1109/TPAMI.2016.2608882 – ident: ref48 doi: 10.1007/978-3-642-33715-4_5 – start-page: 576 year: 2016 ident: ref50 article-title: Robust image and video dehazing with visual artifact suppression via gradient residual minimization publication-title: Proc Eur Conf Comput Vis – start-page: 47 year: 2014 ident: ref13 article-title: Deblurring face images with exemplars publication-title: Proc Eur Conf Comput Vis
SSID	ssj0014503
Score	2.6676357
Snippet	We present an effective blind image deblurring algorithm based on the dark channel prior. The motivation of this work is an interesting observation that the...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	2315
SubjectTerms	Algorithm design and analysis Algorithms Convolution dark channel prior Face Image deblurring Image edge detection Image restoration Kernel linear approximation non-uniform deblurring Optimization Pixels Sparsity
Title	Deblurring Images via Dark Channel Prior
URI	https://ieeexplore.ieee.org/document/8048543 https://www.ncbi.nlm.nih.gov/pubmed/28952935 https://www.proquest.com/docview/2117160049 https://www.proquest.com/docview/1943653315
Volume	40
WOSCitedRecordID	wos000443875500003&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/eLvHCXMwlV3dS-QwEB9UfNAHP0-tX_TAB-Gu2rRp0zyKHyh4sg8K-1bSZHost3alu-vf7yT9QMETfCs0TcN8ZH4zycwAnKQoIsVCHWAkbOjGhIFM7S0LIQohWMGldonC9-LhIRsO5WABfve5MIjoLp_hmX10Z_lmouc2VHaekbglPF6ERSFEk6vVnxjwxHVBJgRDGk5uRJcgE8rzx8HFnzt7i0ucRYTOaRZbAjiTCZm65IM9cg1W_o81nc25Wf_eajdgrcWW_kUjDJuwgNUWrHd9G_xWjbdg9V0Rwm04pS1nbAOB1V__7pm2l6n_OlL-lar_-Tb3oMKxP6hHk_oHPN1cP17eBm3_hEDHCZsFErlSBAkKIyIsRUloR5Wp0WWGKtWs5IqrGLlBVmjOwiIpIs0ERpJrHZnIxDuwVE0q3APfyJRLwnooiph8JCV5qcrQENiKMS0x84B1VMx1W1zc9rgY587JCGXumJBbJuQtEzz41X_z0pTW-HL0tiVxP7KlrgeHHbPyVvumOTm15AZa58eDn_1r0ht7GKIqnMynOZM8TgnrssSD3YbJ_dydbOx__s8DWKGVNVVx2SEszeo5HsGyfp2NpvUxCecwO3bC-Qb-tNtx
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQcKLQ8AgWCxAGJpo0dJ46PFVB1xXa1h0XqzXLsCVqxZFF2t7-fsfMQSIDELVIcx5qH55uxZwbgbYGSG5baBLn0oRuXJqrwtyykrKRklVA2JApP5WxWXl-r-R6cjLkwiBgun-Gpfwxn-W5tdz5UdlaSuOUiuwW3cyE467K1xjMDkYc-yIRhSMfJkRhSZFJ1tpifX038PS55ygmf0zy-CHCpcjJ2-W8WKbRY-TvaDFbn4uD_1vsQHvToMj7vxOER7GFzCAdD54a4V-RDuP9LGcIjeEebzsqHApuv8eQ7bTCb-GZp4o-m_Rb77IMGV_G8Xa7bx_Dl4tPiw2XSd1BIbJazbaJQGEOgoHKSYy1rwjumLpytSzSFZbUwwmQoHLLKCpZWecUtk8iVsJY77rInsN-sG3wGsVOFUIT2UFYZeUlGidrUqSO4lWFRYxkBG6iobV9e3He5WOngZqRKByZozwTdMyGC9-M3P7riGv8cfeRJPI7sqRvB8cAs3evfRpNbS46gd38ieDO-Js3xxyGmwfVuo5kSWUFol-URPO2YPM49yMbzP__zNdy9XFxN9XQy-_wC7tEquxq57Bj2t-0OX8Ide7NdbtpXQUR_Ama93dA
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=Deblurring+Images+via+Dark+Channel+Prior&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Pan%2C+Jinshan&rft.au=Sun%2C+Deqing&rft.au=Pfister%2C+Hanspeter&rft.au=Yang%2C+Ming-Hsuan&rft.date=2018-10-01&rft.eissn=1939-3539&rft.volume=40&rft.issue=10&rft.spage=2315&rft_id=info:doi/10.1109%2FTPAMI.2017.2753804&rft_id=info%3Apmid%2F28952935&rft.externalDocID=28952935
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