Example‐Based Colourization Via Dense Encoding Pyramids

We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Computer graphics forum Ročník 39; číslo 1; s. 20 - 33
Hlavní autoři:	Xiao, Chufeng, Han, Chu, Zhang, Zhuming, Qin, Jing, Wong, Tien‐Tsin, Han, Guoqiang, He, Shengfeng
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Oxford Blackwell Publishing Ltd 01.02.2020
Témata:	Coders Color Computational Photography I.3.3 [Computer Graphics]: Picture/Image; Computing Methodologies: Neural Networks image and video processing Image classification image processing Pyramids Representations
ISSN:	0167-7055, 1467-8659
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization. We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods.
AbstractList	We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization. We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods. We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization. We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a multinomial classification problem. Given a greyscale image and a reference image, the proposed network leverages large‐scale data and then predicts colours by analysing the colour distribution of the reference image. We design the network as a pyramid structure in order to exploit the inherent multi‐scale, pyramidal hierarchy of colour representations. Between two adjacent levels, we propose a hierarchical decoder–encoder filter to pass the colour distributions from the lower level to higher level in order to take both semantic information and fine details into account during the colourization process. Within the network, a novel parallel residual dense block is proposed to effectively extract the local–global context of the colour representations by widening the network. Several experiments, as well as a user study, are conducted to evaluate the performance of our network against state‐of‐the‐art colourization methods. Experimental results show that our network is able to generate colourful, semantically correct and visually pleasant colour images. In addition, unlike fully automatic colourization that produces fixed colour images, the reference image of our network is flexible; both natural images and simple colour palettes can be used to guide the colourization.
Author	Han, Guoqiang Wong, Tien‐Tsin Zhang, Zhuming Han, Chu Qin, Jing Xiao, Chufeng He, Shengfeng
Author_xml	– sequence: 1 givenname: Chufeng surname: Xiao fullname: Xiao, Chufeng email: chufengxiao@outlook.com organization: South China University of Technology – sequence: 2 givenname: Chu orcidid: 0000-0001-7557-9131 surname: Han fullname: Han, Chu email: chan@cse.cuhk.edu.hk organization: The Chinese University of Hong Kong – sequence: 3 givenname: Zhuming surname: Zhang fullname: Zhang, Zhuming email: zhangzm@cse.cuhk.edu.hk organization: The Chinese University of Hong Kong – sequence: 4 givenname: Jing surname: Qin fullname: Qin, Jing email: harry.qin@polyu.edu.hk organization: The Hong Kong Polytechnic University – sequence: 5 givenname: Tien‐Tsin surname: Wong fullname: Wong, Tien‐Tsin email: ttwong@cse.cuhk.edu.hk organization: The Chinese University of Hong Kong – sequence: 6 givenname: Guoqiang surname: Han fullname: Han, Guoqiang email: csgqhan@scut.edu.cn organization: South China University of Technology – sequence: 7 givenname: Shengfeng orcidid: 0000-0002-3802-4644 surname: He fullname: He, Shengfeng email: hesfe@scut.edu.cn organization: South China University of Technology
BookMark	eNp9kL9OwzAQxi1UJNrCwBtEYmJI6z9JHI8Q2oJUCQZgtRz7UrlKk2KnomXiEXhGngTTMiHBLXfD7_vu7hugXtM2gNA5wSMSaqwX1YiwLBVHqE-SjMd5mHuoj0mYOU7TEzTwfokxTniW9pGYbNVqXcPn-8e18mCioq3bjbNvqrNtEz1bFd1A4yGaNLo1tllEDzunVtb4U3RcqdrD2U8foqfp5LG4jef3s7viah5rKriIFReiohWGkmbGVIxqYApMCgy4ICkWSuvclCXLOZSAEyoIY5lKSgWYQZWwIbo4-K5d-7IB38llOLAJKyVlWSI4xXkeqMsDpV3rvYNKrp1dKbeTBMvvZGRIRu6TCez4F6ttt_-3c8rW_ylebQ27v61lMZseFF8jPXdZ
CitedBy_id	crossref_primary_10_1111_cgf_14170 crossref_primary_10_1109_TVCG_2024_3398791 crossref_primary_10_1109_TVCG_2025_3543527 crossref_primary_10_1111_cgf_14791 crossref_primary_10_1016_j_asoc_2025_113010 crossref_primary_10_1016_j_jrras_2024_101285 crossref_primary_10_1109_TCE_2024_3514111 crossref_primary_10_3390_s22197419 crossref_primary_10_1109_TPAMI_2023_3278287 crossref_primary_10_1016_j_ijhcs_2022_102924 crossref_primary_10_1007_s11042_021_10881_5 crossref_primary_10_1111_cgf_13811 crossref_primary_10_1007_s00371_024_03500_5 crossref_primary_10_1109_TIP_2022_3215910 crossref_primary_10_32604_cmes_2022_022369 crossref_primary_10_1016_j_neucom_2024_128121 crossref_primary_10_1109_ACCESS_2020_2994148 crossref_primary_10_1109_TIP_2023_3293777 crossref_primary_10_1016_j_compbiomed_2022_106451 crossref_primary_10_3390_s22207779 crossref_primary_10_1177_0040517520984093 crossref_primary_10_1109_TVCG_2023_3296386 crossref_primary_10_1109_ACCESS_2025_3608008
Cites_doi	10.1111/cgf.13275 10.1007/978-3-319-46493-0_35 10.1145/2508363.2508404 10.1007/978-3-319-46487-9_40 10.1109/CVPR.2017.660 10.1109/CVPR.2016.90 10.1109/TPAMI.2017.2699184 10.5244/C.31.112 10.1145/2897824.2925974 10.1109/TIP.2003.819861 10.1109/TIP.2013.2288929 10.1145/3197517.3201365 10.1109/TMI.2017.2715284 10.1145/566654.566576 10.1145/2393347.2393402 10.1007/978-3-319-10578-9_23 10.1145/1015706.1015780 10.1109/38.946629 10.1145/2766978 10.1111/cgf.12008 10.1109/CVPR.2009.5206757 10.1109/TPAMI.2016.2644615 10.1109/ICCV.2017.168 10.1109/CVPR.2017.243 10.1145/1015706.1015720 10.1109/ICCV.2015.55 10.1007/s11263-015-0816-y 10.1109/CVPR.2017.544 10.1109/ICCV.2005.239 10.1007/978-3-030-01234-2_18 10.1145/1141911.1142017 10.1145/987657.987677 10.1145/3072959.3073703
ContentType	Journal Article
Copyright	2019 The Authors Computer Graphics Forum © 2019 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd
Copyright_xml	– notice: 2019 The Authors Computer Graphics Forum © 2019 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd – notice: 2020 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd
DBID	AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1111/cgf.13659
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	33
ExternalDocumentID	10_1111_cgf_13659 CGF13659
Genre	article
GrantInformation_xml	– fundername: Special Fund of Science and Technology Research and Development on Application From Guangdong Province funderid: 2016B010127003 – fundername: Innovation and Technology Fund of Hong Kong funderid: ITS/319/17 – fundername: Shenzhen Science and Technology Program funderid: JCYJ20160429190300857 – fundername: RGC General Research Fund funderid: CUHK14201017 – fundername: Guangzhou Key Industrial Technology Research fund funderid: 201802010036 – fundername: National Natural Science Foundation of China funderid: 61472145; 61702194 – fundername: Guangdong Natural Science Foundation funderid: 2017A030312008
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 AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABDPE ABEML ABPVW ACAHQ ACBWZ ACCFJ ACCZN ACFBH ACGFS ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEGXH AEIGN AEIMD AEMOZ AENEX AEQDE AEUQT AEUYR AFBPY AFEBI AFFNX AFFPM AFGKR AFPWT AFWVQ AFZJQ AHBTC AHEFC AHQJS AITYG AIURR AIWBW AJBDE 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 WRC WXSBR WYISQ WZISG XG1 ZL0 ZZTAW ~IA ~IF ~WT AAMMB AAYXX ADMLS AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c2979-a799f2f0eb26ddf32ce3aed5e3e791509acc8dbb387ebe04291336a4bae03ef43
IEDL.DBID	DRFUL
ISICitedReferencesCount	37
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000519969500003&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	Sun Jul 13 03:24:16 EDT 2025 Tue Nov 18 21:57:38 EST 2025 Sat Nov 29 03:41:16 EST 2025 Wed Jan 22 16:34:29 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2979-a799f2f0eb26ddf32ce3aed5e3e791509acc8dbb387ebe04291336a4bae03ef43
Notes	Joint first authors. Corresponding author. ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-7557-9131 0000-0002-3802-4644
PQID	2364972088
PQPubID	30877
PageCount	14
ParticipantIDs	proquest_journals_2364972088 crossref_primary_10_1111_cgf_13659 crossref_citationtrail_10_1111_cgf_13659 wiley_primary_10_1111_cgf_13659_CGF13659
PublicationCentury	2000
PublicationDate	February 2020 2020-02-00 20200201
PublicationDateYYYYMMDD	2020-02-01
PublicationDate_xml	– month: 02 year: 2020 text: February 2020
PublicationDecade	2020
PublicationPlace	Oxford
PublicationPlace_xml	– name: Oxford
PublicationTitle	Computer graphics forum
PublicationYear	2020
Publisher	Blackwell Publishing Ltd
Publisher_xml	– name: Blackwell Publishing Ltd
References	2015; 34 2012 2011 2004; 23 2009 2007 2006 2005 2018; 40 2004 2002 2014; 23 2016; 35 2001; 21 2015; 115 2017; 36 2013; 32 2017; 39 2004; 13 2018 2017 2016 2015 2014 2013 2018; 37 e_1_2_7_6_1 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 e_1_2_7_8_1 e_1_2_7_7_1 e_1_2_7_19_1 e_1_2_7_17_1 e_1_2_7_16_1 e_1_2_7_40_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_14_1 Lazebnik S. (e_1_2_7_23_1) 2006 e_1_2_7_42_1 e_1_2_7_13_1 e_1_2_7_43_1 e_1_2_7_12_1 e_1_2_7_44_1 e_1_2_7_11_1 e_1_2_7_45_1 e_1_2_7_10_1 Tai Y.‐W. (e_1_2_7_32_1) 2005 e_1_2_7_26_1 e_1_2_7_27_1 e_1_2_7_28_1 e_1_2_7_29_1 Mao X. (e_1_2_7_25_1) 2016 Glorot X. (e_1_2_7_9_1) 2011 Ironi R. (e_1_2_7_18_1) 2005 e_1_2_7_30_1 e_1_2_7_31_1 e_1_2_7_33_1 e_1_2_7_22_1 e_1_2_7_34_1 Zhou B. (e_1_2_7_41_1) 2014 e_1_2_7_21_1 e_1_2_7_35_1 e_1_2_7_20_1 e_1_2_7_36_1 Luan Q. (e_1_2_7_24_1) 2007 e_1_2_7_37_1 e_1_2_7_38_1 e_1_2_7_39_1
References_xml	– volume: 37 start-page: 47:1 issue: 4 year: 2018 end-page: 47:16 article-title: Deep exemplar‐based colorization publication-title: ACM Transactions on Graphics – start-page: 346 year: 2014 end-page: 361 – start-page: 3 year: 2017 – start-page: 1458 year: 2005 end-page: 1465 – start-page: 315 year: 2011 end-page: 323 – start-page: 121 year: 2004 end-page: 127 – start-page: 201 year: 2005 end-page: 210 – volume: 23 start-page: 309 year: 2004 end-page: 314 article-title: Grabcut: Interactive foreground extraction using iterated graph cuts publication-title: ACM Transactions on Graphics – start-page: 770 year: 2016 end-page: 778 – volume: 36 start-page: 2524 issue: 12 year: 2017 end-page: 2535 article-title: Low‐dose CT with a residual encoder‐decoder convolutional neural network publication-title: IEEE Transactions on Medical Imaging – start-page: 93 year: 2017 end-page: 103 article-title: L0 gradient‐preserving color transfer publication-title: Computer Graphics Forum 36 – volume: 35 start-page: 110:1 issue: 4 year: 2016 end-page: 110:11 article-title: Let there be color!: Joint end‐to‐end learning of global and local image priors for automatic image colorization with simultaneous classification publication-title: ACM Transactions on Graphics – start-page: 2802 year: 2016 end-page: 2810 – start-page: 487 year: 2014 end-page: 495 – start-page: 689 year: 2004 end-page: 694 article-title: Colorization using optimization publication-title: ACM Transactions on Graphics 23 – start-page: 309 year: 2007 end-page: 320 – start-page: 1214 year: 2006 end-page: 1220 article-title: Manga colorization publication-title: ACM Transactions on Graphics 25 – volume: 23 start-page: 298 issue: 1 year: 2014 end-page: 307 article-title: Variational exemplar‐based image colorization publication-title: IEEE Transactions on Image Processing – start-page: 2881 year: 2017 end-page: 2890 – volume: 40 start-page: 834 issue: 4 year: 2018 end-page: 848 article-title: DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 277 year: 2002 end-page: 280 article-title: Transferring color to greyscale images publication-title: ACM Transactions on Graphics 21 – start-page: 190 year: 2013 end-page: 203 article-title: Content‐based colour transfer publication-title: Computer Graphics Forum 32 – start-page: 286 year: 2018 end-page: 301 – start-page: 1794 year: 2009 end-page: 1801 – start-page: 415 year: 2015 end-page: 423 – volume: 36 start-page: 119:1 issue: 4 year: 2017 end-page: 119:11 article-title: Real‐time user‐guided image colorization with learned deep priors publication-title: ACM Transactions on Graphics – start-page: 2169 year: 2006 end-page: 2178 – volume: 21 start-page: 34 issue: 5 year: 2001 end-page: 41 article-title: Color transfer between images publication-title: IEEE Computer Graphics and Applications – start-page: 747 year: 2005 end-page: 754 – volume: 34 start-page: 139:1 issue: 4 year: 2015 end-page: 139:11 article-title: Palette‐based photo recoloring publication-title: ACM Transactions on Graphics – start-page: 369 year: 2012 end-page: 378 – start-page: 577 year: 2016 end-page: 593 – start-page: 649 year: 2016 end-page: 666 – volume: 39 start-page: 2481 issue: 12 year: 2017 end-page: 2495 article-title: Segnet: A deep convolutional encoder‐decoder architecture for image segmentation publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 32 start-page: 197:1 issue: 6 year: 2013 end-page: 197:10 article-title: A sparse control model for image and video editing publication-title: ACM Transactions on Graphics – year: 2017 – volume: 13 start-page: 600 issue: 4 year: 2004 end-page: 612 article-title: Image quality assessment: From error visibility to structural similarity publication-title: IEEE Transactions on Image Processing – volume: 115 start-page: 211 issue: 3 year: 2015 end-page: 252 article-title: Imagenet large scale visual recognition challenge publication-title: International Journal of Computer Vision – start-page: 2169 volume-title: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition year: 2006 ident: e_1_2_7_23_1 – ident: e_1_2_7_20_1 – ident: e_1_2_7_36_1 doi: 10.1111/cgf.13275 – start-page: 315 volume-title: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics year: 2011 ident: e_1_2_7_9_1 – ident: e_1_2_7_22_1 doi: 10.1007/978-3-319-46493-0_35 – ident: e_1_2_7_37_1 doi: 10.1145/2508363.2508404 – ident: e_1_2_7_39_1 doi: 10.1007/978-3-319-46487-9_40 – ident: e_1_2_7_42_1 doi: 10.1109/CVPR.2017.660 – ident: e_1_2_7_17_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_7_6_1 doi: 10.1109/TPAMI.2017.2699184 – ident: e_1_2_7_12_1 doi: 10.5244/C.31.112 – ident: e_1_2_7_19_1 doi: 10.1145/2897824.2925974 – ident: e_1_2_7_34_1 doi: 10.1109/TIP.2003.819861 – ident: e_1_2_7_3_1 doi: 10.1109/TIP.2013.2288929 – ident: e_1_2_7_13_1 doi: 10.1145/3197517.3201365 – ident: e_1_2_7_8_1 doi: 10.1109/TMI.2017.2715284 – start-page: 487 volume-title: Proceedings of International Conference on Neural Information Processing Systems year: 2014 ident: e_1_2_7_41_1 – ident: e_1_2_7_33_1 doi: 10.1145/566654.566576 – ident: e_1_2_7_10_1 doi: 10.1145/2393347.2393402 – ident: e_1_2_7_16_1 doi: 10.1007/978-3-319-10578-9_23 – start-page: 2802 volume-title: Proceedings of International Conference on Neural Information Processing Systems year: 2016 ident: e_1_2_7_25_1 – ident: e_1_2_7_21_1 doi: 10.1145/1015706.1015780 – ident: e_1_2_7_27_1 doi: 10.1109/38.946629 – ident: e_1_2_7_4_1 doi: 10.1145/2766978 – ident: e_1_2_7_30_1 – ident: e_1_2_7_35_1 doi: 10.1111/cgf.12008 – ident: e_1_2_7_38_1 doi: 10.1109/CVPR.2009.5206757 – ident: e_1_2_7_2_1 doi: 10.1109/TPAMI.2016.2644615 – ident: e_1_2_7_5_1 doi: 10.1109/ICCV.2017.168 – ident: e_1_2_7_14_1 doi: 10.1109/CVPR.2017.243 – ident: e_1_2_7_29_1 doi: 10.1145/1015706.1015720 – ident: e_1_2_7_7_1 doi: 10.1109/ICCV.2015.55 – ident: e_1_2_7_28_1 doi: 10.1007/s11263-015-0816-y – ident: e_1_2_7_43_1 – ident: e_1_2_7_45_1 doi: 10.1109/CVPR.2017.544 – start-page: 201 volume-title: Proceedings of Eurographics Conference on Rendering Techniques year: 2005 ident: e_1_2_7_18_1 – start-page: 747 volume-title: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 year: 2005 ident: e_1_2_7_32_1 – ident: e_1_2_7_11_1 doi: 10.1109/ICCV.2005.239 – ident: e_1_2_7_40_1 doi: 10.1007/978-3-030-01234-2_18 – start-page: 309 volume-title: Proceedings of the 18th Eurographics Conference on Rendering Techniques year: 2007 ident: e_1_2_7_24_1 – ident: e_1_2_7_26_1 doi: 10.1145/1141911.1142017 – ident: e_1_2_7_31_1 doi: 10.1145/987657.987677 – ident: e_1_2_7_44_1 doi: 10.1145/3072959.3073703 – ident: e_1_2_7_15_1
SSID	ssj0004765
Score	2.489928
Snippet	We propose a novel deep example‐based image colourization method called dense encoding pyramid network. In our study, we define the colourization as a...
SourceID	proquest crossref wiley
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	20
SubjectTerms	Coders Color Computational Photography I.3.3 [Computer Graphics]: Picture/Image; Computing Methodologies: Neural Networks image and video processing Image classification image processing Pyramids Representations
Title	Example‐Based Colourization Via Dense Encoding Pyramids
URI	https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.13659 https://www.proquest.com/docview/2364972088
Volume	39
WOSCitedRecordID	wos000519969500003&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/eLvHCXMwpV1LS8NAEB5q60EPvsVqlSAevATa3c1j8aR96KGUIlZ6C5t9SEFTSVrRmz_B3-gvcXebtBUUBG85TJJldma-mWXmW4AzjCjzNAy7hHvYJYQSNxS47jKNlp7ilCBu2fW7Qa8XDoe0X4KLYhZmxg8xP3AznmHjtXFwFmdLTs4flO3RoitQQdpuSRkqrdvOoLsYiwx8r6D2NqQxObGQaeSZv_wdjhY55nKmaqGms_mvRW7BRp5hOpczk9iGkkx2YH2Jd3AXaPuVGVbgz_ePK41iwmnqEDhN85FM537EnJYub6XTTvjYgJvTf0vZ00hkezDotO-aN25-h4LLEQ2oywJKFVJ1XUD7QiiMuMRMCk9iGVCdDFLGeSjiGIeB3k6DTrpo9RmJmaxjqQjeh3IyTuQBODjmHmfKx8JweDV0LqEoikkj4KEiXKAqnBeqjHhOMG7uuXiMikJDayOy2qjC6Vz0ecaq8ZNQrdiPKHesLDJ89zRAOjbq31nN__6BqHndsQ-Hfxc9gjVkKmrbl12D8iSdymNY5S-TUZae5Bb2BRcQ01Y
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qK6gH32K1ahAPXgLt7uax4EX7sGIsRVrxFjb7kIKm0ofozZ_gb_SXuJsmbQUFwVsOk02YnZlvZpn5FuAEI8ocDcM24Q62CaHE9gUu20yjpaM4JYgn7PqB12r59_e0nYOzbBZmwg8xPXAznpHEa-Pg5kB6zsv5g0qatOgCFIg2IycPhdptoxvM5iI918m4vQ1rTMosZDp5pi9_x6NZkjmfqiZY01j731-uw2qaY1rnE6PYgJyMN2FljnlwC2j9lRle4M_3jwuNY8Kq6iA4HqRDmdZdj1k1XeBKqx7zvoE3q_02YE89MdyGbqPeqTbt9BYFmyPqUZt5lCqkyrqEdoVQGHGJmRSOxNKjOh2kjHNfRBH2Pb2hBp902eoyEjFZxlIRvAP5uB_LXbBwxB3OlIuFYfGq6GxCURSRisd9RbhARTjNdBnylGLc3HTxGGalhtZGmGijCMdT0ecJr8ZPQqVsQ8LUtYahYbynHtLRUX8uUf3vC4TVy0bysPd30SNYanZugjC4al3vwzIy9XXSpV2C_GgwlgewyF9GveHgMDW3L8fq10Y
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB5qFdGDb7FaNYgHL4F2d_NY8KJto2IpRaz0Fjb7kIKmJW1Fb_4Ef6O_xN00aSsoCN5ymDyY3ZlvvjDzLcApRpQ5GoZtwh1sE0KJ7QtcsZlGS0dxShBP1fWbXqvld7u0XYDzfBZmog8x_eFmIiPN1ybA5UCouSjnjypt0qILsEgc6uqwXKzfBZ3mbC7Sc51c29uoxmTKQqaTZ3rzdzyaFZnzpWqKNcH6_75yA9ayGtO6mGyKTSjIeAtW55QHt4E2XpnRBf58_7jUOCasmk6C4yQbyrQeesyqa4IrrUbM-wberPZbwp57YrgDnaBxX7u2s1MUbI6oR23mUaqQqmgK7QqhMOISMykciaVHdTlIGee-iCLse3pBDT5p2uoyEjFZwVIRvAvFuB_LPbBwxB3OlIuFUfGq6mpCURSRqsd9RbhAJTjLfRnyTGLcnHTxFOZUQ3sjTL1RgpOp6WCiq_GTUTlfkDALrWFoFO-ph3R21K9LXf_7A8LaVZBe7P_d9BiW2_UgbN60bg9gBRl6nTZpl6E4SsbyEJb4y6g3TI6y3fYFjqHWwQ
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=Example%E2%80%90Based+Colourization+Via+Dense+Encoding+Pyramids&rft.jtitle=Computer+graphics+forum&rft.au=Xiao%2C+Chufeng&rft.au=Chu%2C+Han&rft.au=Zhang%2C+Zhuming&rft.au=Qin%2C+Jing&rft.date=2020-02-01&rft.pub=Blackwell+Publishing+Ltd&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=39&rft.issue=1&rft.spage=20&rft.epage=33&rft_id=info:doi/10.1111%2Fcgf.13659&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