Task-Oriented Network for Image Dehazing

Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accord...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on image processing Vol. 29; pp. 6523 - 6534
Main Authors:	Li, Runde, Pan, Jinshan, He, Min, Li, Zechao, Tang, Jinhui
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.01.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Artificial neural networks Atmospheric modeling Coders Convolutional neural networks Distortion Haze Image color analysis image dehazing Image restoration Image transmission multi-stage dehazing algorithm Neural networks Recurrent neural networks Task analysis Task-oriented network
ISSN:	1057-7149, 1941-0042, 1941-0042
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-by-step fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods.
AbstractList	Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-bystep fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods.Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-bystep fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods. Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-by-step fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods. Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image dehazing algorithms usually use some common networks. The network design does not model the image formation of haze process well, which accordingly leads to dehazed images containing artifacts and haze residuals in some special scenes. In this paper, we propose a task-oriented network for image dehazing, where the network design is motivated by the image formation of haze process. The task-oriented network involves a hybrid network containing an encoder and decoder network and a spatially variant recurrent neural network which is derived from the hazy process. In addition, we develop a multi-stage dehazing algorithm to further improve the accuracy by filtering haze residuals in a step-bystep fashion. To constrain the proposed network, we develop a dual composition loss, content-based pixel-wise loss and total variation constraint. We train the proposed network in an end-to-end manner and analyze its effect on image dehazing. Experimental results demonstrate that the proposed algorithm achieves favorable performance against state-of-the-art dehazing methods.
Author	Pan, Jinshan Li, Runde Tang, Jinhui Li, Zechao He, Min
Author_xml	– sequence: 1 givenname: Runde orcidid: 0000-0002-3204-6359 surname: Li fullname: Li, Runde email: rundeli@njust.edu.cn organization: School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 2 givenname: Jinshan surname: Pan fullname: Pan, Jinshan email: jspan@njust.edu.cn organization: School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 3 givenname: Min orcidid: 0000-0002-7785-9409 surname: He fullname: He, Min email: paper_review@126.com organization: College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, China – sequence: 4 givenname: Zechao orcidid: 0000-0002-5341-5985 surname: Li fullname: Li, Zechao email: zechao.li@njust.edu.cn organization: School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China – sequence: 5 givenname: Jinhui orcidid: 0000-0001-9008-222X surname: Tang fullname: Tang, Jinhui email: jinhuitang@njust.edu.cn organization: School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32386154$$D View this record in MEDLINE/PubMed
BookMark	eNp9kD1PwzAQQC1UBC2wIyGhSixdUs7OObZHVL4qIWAoc-QkZwi0CdipEPx6XLUwdGDyDe_dWW_Aek3bEGPHHMacgzmfTR_HAgSMhTFcgtlhfW6QJwAoenEGqRLF0eyzQQivABwlz_bYfipSnXGJfTaa2fCWPPiamo6q4T11n61_G7rWD6cL-0zDS3qx33XzfMh2nZ0HOtq8B-zp-mo2uU3uHm6mk4u7pExRdYnlqCpeOq1Mxktp08KVpshAOGU1AWqnMyWLAq3OZFlhVrlCWGfQpcoSqPSAjdZ73337saTQ5Ys6lDSf24baZcgFAkjBpcaInm2hr-3SN_F3kYodDCLySJ1uqGWxoCp_9_XC-q_8t0EEYA2Uvg3Bk_tDOOSrzHnMnK8y55vMUcm2lLLubFe3TedtPf9PPFmLNRH93TGgtUCd_gClUIaa
CODEN	IIPRE4
CitedBy_id	crossref_primary_10_1109_ACCESS_2021_3050260 crossref_primary_10_1109_TIP_2020_3044208 crossref_primary_10_1007_s00371_022_02493_3 crossref_primary_10_1016_j_patcog_2021_108076 crossref_primary_10_3390_rs14081852 crossref_primary_10_1109_JOE_2021_3064093 crossref_primary_10_1016_j_image_2023_117033 crossref_primary_10_1145_3576918 crossref_primary_10_1109_LSP_2023_3304540 crossref_primary_10_3390_rs15040938 crossref_primary_10_3390_s22031199 crossref_primary_10_1007_s13042_022_01753_x crossref_primary_10_1109_TPAMI_2024_3416731 crossref_primary_10_1007_s00521_024_09969_4 crossref_primary_10_1080_01969722_2023_2176624 crossref_primary_10_1049_ipr2_12506 crossref_primary_10_3390_s23167026 crossref_primary_10_1016_j_micpro_2021_104079 crossref_primary_10_1109_ACCESS_2022_3188860 crossref_primary_10_1109_TIP_2023_3286263 crossref_primary_10_1109_TIP_2021_3116790 crossref_primary_10_3390_s21082625 crossref_primary_10_3390_s21113896 crossref_primary_10_1109_TIP_2023_3333564 crossref_primary_10_3390_s23218932 crossref_primary_10_1109_TGRS_2023_3261545 crossref_primary_10_1016_j_jvcir_2022_103720 crossref_primary_10_1109_TIP_2021_3078319 crossref_primary_10_1109_ACCESS_2025_3576646 crossref_primary_10_1016_j_optlastec_2025_113542 crossref_primary_10_1016_j_sigpro_2021_108396 crossref_primary_10_1109_ACCESS_2021_3099224 crossref_primary_10_1016_j_engappai_2023_106001 crossref_primary_10_1007_s13042_023_01782_0 crossref_primary_10_3390_rs16020225 crossref_primary_10_1109_TAI_2022_3204732
Cites_doi	10.1007/978-3-030-01237-3_32 10.1007/978-3-030-01234-2_43 10.1109/TPAMI.2003.1201821 10.1109/CVPR.2014.383 10.24963/ijcai.2018/172 10.1109/ICCPHOT.2014.6831817 10.1109/CVPR.2018.00856 10.1007/978-3-319-46475-6_36 10.1109/CVPR.2018.00778 10.1109/TIP.2016.2598681 10.1145/2647868.2654889 10.1109/ICCV.2013.82 10.1145/3240508.3240694 10.1109/CVPR.2018.00324 10.1109/TPAMI.2010.168 10.1007/978-3-319-46493-0_34 10.1145/2651362 10.1109/CVPR.2018.00343 10.1109/CVPR.2017.35 10.1109/TIP.2013.2262284 10.1109/CVPR.2019.00835 10.1109/CVPR.2019.01195 10.1007/978-3-642-33715-4_54 10.1109/CVPR.2018.00337 10.1007/s11263-011-0508-1 10.1109/ICIP.2017.8296874 10.1109/TPAMI.2015.2505283 10.1109/TIP.2018.2867951 10.1109/CVPR.2018.00267 10.1007/978-3-319-46475-6_10 10.1109/ICCV.2017.511 10.1109/WACV.2019.00151 10.1109/ICIP.2010.5651263 10.1109/CVPR.2016.185 10.1007/978-3-319-46475-6_43 10.1016/j.cviu.2017.09.003 10.1109/ICCV.2017.351 10.1109/CVPRW.2018.00127 10.1109/ICCV.1999.790306 10.1109/CVPR.2017.243 10.1109/TIP.2015.2446191
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TIP.2020.2991509
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) 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	MEDLINE - Academic Technology Research Database 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/IET Electronic Library (IEL) (UW System Shared) 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	Applied Sciences Engineering
EISSN	1941-0042
EndPage	6534
ExternalDocumentID	32386154 10_1109_TIP_2020_2991509 9088248
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Natural Science Foundation of Jiangsu Province grantid: BK20180471 funderid: 10.13039/501100004608 – fundername: National Natural Science Foundation of China grantid: 61922043; 61925204; 61872421 funderid: 10.13039/501100001809 – fundername: National Basic Research Program of China (973 Program); National Key Research and Development Program of China grantid: 2018AAA0102002 funderid: 10.13039/501100012166
GroupedDBID	--- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION NPM Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c347t-a147d1cf87961c5a3bfc9b602f7a8e048f8675bb4a865cd46dfb2af94f37ae073
IEDL.DBID	RIE
ISICitedReferencesCount	41
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000545079400011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1057-7149 1941-0042
IngestDate	Sat Sep 27 20:55:17 EDT 2025 Mon Jun 30 10:23:03 EDT 2025 Wed Feb 19 02:09:39 EST 2025 Tue Nov 18 21:52:29 EST 2025 Sat Nov 29 03:21:12 EST 2025 Wed Aug 27 02:37:45 EDT 2025
IsPeerReviewed	true
IsScholarly	true
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-c347t-a147d1cf87961c5a3bfc9b602f7a8e048f8675bb4a865cd46dfb2af94f37ae073
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-7785-9409 0000-0002-3204-6359 0000-0001-9008-222X 0000-0002-5341-5985
PMID	32386154
PQID	2419494441
PQPubID	85429
PageCount	12
ParticipantIDs	pubmed_primary_32386154 proquest_journals_2419494441 crossref_primary_10_1109_TIP_2020_2991509 proquest_miscellaneous_2400521584 crossref_citationtrail_10_1109_TIP_2020_2991509 ieee_primary_9088248
PublicationCentury	2000
PublicationDate	2020-01-01
PublicationDateYYYYMMDD	2020-01-01
PublicationDate_xml	– month: 01 year: 2020 text: 2020-01-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on image processing
PublicationTitleAbbrev	TIP
PublicationTitleAlternate	IEEE Trans Image Process
PublicationYear	2020
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	ref35 ref13 ref34 ref12 mei (ref17) 2018 ref37 ref15 ref36 ref14 ref31 ref30 ref11 ref32 ref10 ref2 ref1 ref39 ref16 ref19 ref18 he (ref8) 2011; 33 kingma (ref45) 2015 ref46 ref24 ref23 ref26 ref20 ref42 ref41 ref22 ref44 liu (ref33) 2018 ref21 ref43 yang (ref25) 2018 ref28 ref27 ref29 ref7 ref9 ref4 ref3 ref6 ref5 ref40 dosovitskiy (ref38) 2016
References_xml	– ident: ref34 doi: 10.1007/978-3-030-01237-3_32 – ident: ref27 doi: 10.1007/978-3-030-01234-2_43 – ident: ref1 doi: 10.1109/TPAMI.2003.1201821 – ident: ref20 doi: 10.1109/CVPR.2014.383 – ident: ref26 doi: 10.24963/ijcai.2018/172 – ident: ref21 doi: 10.1109/ICCPHOT.2014.6831817 – ident: ref14 doi: 10.1109/CVPR.2018.00856 – ident: ref7 doi: 10.1007/978-3-319-46475-6_36 – ident: ref30 doi: 10.1109/CVPR.2018.00778 – ident: ref12 doi: 10.1109/TIP.2016.2598681 – ident: ref46 doi: 10.1145/2647868.2654889 – ident: ref9 doi: 10.1109/ICCV.2013.82 – ident: ref35 doi: 10.1145/3240508.3240694 – ident: ref40 doi: 10.1109/CVPR.2018.00324 – volume: 33 start-page: 2341 year: 2011 ident: ref8 article-title: Single image haze removal using dark channel prior publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2010.168 – ident: ref29 doi: 10.1007/978-3-319-46493-0_34 – ident: ref23 doi: 10.1145/2651362 – ident: ref15 doi: 10.1109/CVPR.2018.00343 – start-page: 203 year: 2018 ident: ref17 article-title: Progressive feature fusion network for realistic image Dehazing publication-title: Proc Asian Conf Comput Vis – ident: ref36 doi: 10.1109/CVPR.2017.35 – ident: ref5 doi: 10.1109/TIP.2013.2262284 – start-page: 7485 year: 2018 ident: ref25 article-title: Towards perceptual image Dehazing by physics-based disentanglement and adversarial training publication-title: Proc 22nd AAAI Conf Artif Intell – ident: ref4 doi: 10.1109/CVPR.2019.00835 – ident: ref28 doi: 10.1109/CVPR.2019.01195 – ident: ref41 doi: 10.1007/978-3-642-33715-4_54 – ident: ref16 doi: 10.1109/CVPR.2018.00337 – ident: ref19 doi: 10.1007/s11263-011-0508-1 – ident: ref44 doi: 10.1109/ICIP.2017.8296874 – ident: ref42 doi: 10.1109/TPAMI.2015.2505283 – ident: ref43 doi: 10.1109/TIP.2018.2867951 – start-page: 658 year: 2016 ident: ref38 article-title: Generating images with perceptual similarity metrics based on deep networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref32 doi: 10.1109/CVPR.2018.00267 – ident: ref3 doi: 10.1007/978-3-319-46475-6_10 – ident: ref24 doi: 10.1109/ICCV.2017.511 – year: 2015 ident: ref45 article-title: Adam: A method for stochastic optimization publication-title: Proc Int Conf Learn Represent – ident: ref18 doi: 10.1109/WACV.2019.00151 – ident: ref22 doi: 10.1109/ICIP.2010.5651263 – ident: ref6 doi: 10.1109/CVPR.2016.185 – ident: ref39 doi: 10.1007/978-3-319-46475-6_43 – start-page: 182 year: 2018 ident: ref33 article-title: Multiple connected residual network for image enhancement on smartphones publication-title: Proc Eur Conf Comput Vis Workshops – ident: ref11 doi: 10.1016/j.cviu.2017.09.003 – ident: ref31 doi: 10.1109/ICCV.2017.351 – ident: ref13 doi: 10.1109/CVPRW.2018.00127 – ident: ref2 doi: 10.1109/ICCV.1999.790306 – ident: ref37 doi: 10.1109/CVPR.2017.243 – ident: ref10 doi: 10.1109/TIP.2015.2446191
SSID	ssj0014516
Score	2.5083075
Snippet	Haze interferes the transmission of scene radiation and significantly degrades color and details of outdoor images. Existing deep neural networks-based image...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	6523
SubjectTerms	Algorithms Artificial neural networks Atmospheric modeling Coders Convolutional neural networks Distortion Haze Image color analysis image dehazing Image restoration Image transmission multi-stage dehazing algorithm Neural networks Recurrent neural networks Task analysis Task-oriented network
Title	Task-Oriented Network for Image Dehazing
URI	https://ieeexplore.ieee.org/document/9088248 https://www.ncbi.nlm.nih.gov/pubmed/32386154 https://www.proquest.com/docview/2419494441 https://www.proquest.com/docview/2400521584
Volume	29
WOSCitedRecordID	wos000545079400011&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ1LS8QwEIAHFQ968P2oj6WCBwXj9pHmcRR10cvqYYW9lSRNVNRd2Ye_30nbLQoqeCs0TcMkk3yTSWYAjkXhuHaSERMpRdD-okTLQhIrmIuZkEZrUyab4N2u6Pfl_RycNXdhrLXl4TN77h9LX34xNFO_Vdb2Z3ISKuZhnnNW3dVqPAY-4Wzp2cw44Yj9M5dkJNu923s0BJPoHKde5B_5bQkqc6r8jpflMtNZ_V8D12Clxsnwour_dZizgw1YrdEyrBV3vAHLX-IObsJJT41fyJ0PcYzAGXaro-Ah8mt4-4YTTHhln3zY6ccteOhc9y5vSJ0ygZiU8glRMeVFbJzgksUmU6l2RmoWJY4rYVFbnUALQWuqBMtMQVnhdKKcpC7lyqK6b8PCYDiwuxBqrEUhT8TMUx2NNC-M9VFsmcqyxKUBtGdSzE0dT9yntXjNS7sikjnKPfdyz2u5B3DafPFexdL4o-ymF29TrpZsAAezjsprZRvnCCGSSopgF8BR8xrVxPs-1MAOp76M3wCPEbcC2Kk6uKk7RWxBsKN7P_9zH5Z8y6p9lwNYmIym9hAWzcfkeTxq4Vjsi1Y5Fj8BY4zYPA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlZ3dT9swEMBPfEkbDxQog7ACmcQDk3CbD8cfj9MAUQGlD0XiLbIde5sGLaItfz_nJI02iU3iLVIcxzr77N_57DuAY1E4rp1kxERKEbS_KNGykMQK5mImpNHalMkm-GAg7u_lcAlOm7sw1try8Jnt-sfSl19MzNxvlfX8mZyEimVYzShNouq2VuMz8ClnS99mxglH8F84JSPZG_WHaAomURcnXyQg-dciVGZV-TdglgvNRet9TdyEjRoow2_VCNiCJTvehlYNl2GtutNtWP8j8mAbTkZq-pvc-iDHiJzhoDoMHiLBhv1HnGLCM_vTB57-sQN3F-ej75ekTppATEr5jKiY8iI2TnDJYpOpVDsjNYsSx5WwqK9OoI2gNVWCZaagrHA6UU5Sl3JlUeE_wcp4MrZ7EGqsRSFRxMxzHY00L4z1cWyZyrLEpQH0FlLMTR1R3Ce2eMhLyyKSOco993LPa7kH8LX54qmKpvGfsm0v3qZcLdkAOouOymt1m-aIIZJKimgXwJfmNSqK936osZ3MfRm_BR4jcAWwW3VwU3eK4IJoR_ff_ucRfLgc3Vzn1_3B1Wf46FtZ7cJ0YGX2PLcHsGZeZr-mz4fliHwFtNPamw
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=Task-Oriented+Network+for+Image+Dehazing&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Runde%2C+Li&rft.au=Pan%2C+Jinshan&rft.au=He%2C+Min&rft.au=Li%2C+Zechao&rft.date=2020-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=29&rft.spage=6523&rft_id=info:doi/10.1109%2FTIP.2020.2991509&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon