Scale-Free Single Image Deraining Via Visibility-Enhanced Recurrent Wavelet Learning
In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen and thus are visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak...
Uloženo v:
| Vydáno v: | IEEE transactions on image processing Ročník 28; číslo 6; s. 2948 - 2961 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
IEEE
01.06.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1057-7149, 1941-0042, 1941-0042 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen and thus are visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component and 2) recurrent detail recovery on high-frequency components under the guidance of the recovered low-frequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus it can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation of both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods. |
|---|---|
| AbstractList | In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen and thus are visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component and 2) recurrent detail recovery on high-frequency components under the guidance of the recovered low-frequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus it can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation of both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods. In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen, and thus visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to a poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component; 2) recurrent detail recovery on highfrequency components under the guidance of the recovered lowfrequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation on both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-ofthe- art methods. In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen, and thus visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to a poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component; 2) recurrent detail recovery on highfrequency components under the guidance of the recovered lowfrequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation on both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-ofthe- art methods.In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen, and thus visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to a poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component; 2) recurrent detail recovery on highfrequency components under the guidance of the recovered lowfrequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation on both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-ofthe- art methods. |
| Author | Shuai Yang Jiaying Liu Wenhan Yang Zongming Guo |
| Author_xml | – sequence: 1 givenname: Wenhan orcidid: 0000-0002-1692-0069 surname: Yang fullname: Yang, Wenhan – sequence: 2 givenname: Jiaying orcidid: 0000-0002-0468-9576 surname: Liu fullname: Liu, Jiaying – sequence: 3 givenname: Shuai orcidid: 0000-0002-5576-8629 surname: Yang fullname: Yang, Shuai – sequence: 4 givenname: Zongming orcidid: 0000-0002-4944-9621 surname: Guo fullname: Guo, Zongming |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30640610$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kU1LxDAQhoMofqzeBUEKXrx0naRpmxxFXV1YUHTVY0jTqUa6qSat4L83y64ePHgYMoTnna93j2y6ziEhhxTGlII8m0_vxgyoHDMhWSHyDbJLJacpAGebMYe8TEvK5Q7ZC-ENgPKcFttkJ4OCQ0Fhl8wfjG4xnXjE5MG6lxaT6UK_YHKJXlsXf5Inq2MEW9nW9l_plXvVzmCd3KMZvEfXJ8_6E1vskxlqv5Tsk61GtwEP1u-IPE6u5hc36ez2enpxPktNxss-xVyXLAeODa-NASZi1biIYCjQ0JpXjeaiBk15xnkmtGGmyptS6oqVWEqZjcjpqu677z4GDL1a2GCwbbXDbgiK0VJmRdxTRPTkD_rWDd7F6RRjFCCTBRSROl5TQ7XAWr17u9D-S_3cKwKwAozvQvDY_CIU1NISFS1RS0vU2pIoKf5IjO11bzvXxwu3_wmPVkKLiL99xHIMlmffpiiWvQ |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_1007_s11432_020_3225_9 crossref_primary_10_1016_j_patcog_2023_109740 crossref_primary_10_1007_s00034_024_02762_7 crossref_primary_10_1017_S0373463321000783 crossref_primary_10_1109_TPAMI_2022_3186629 crossref_primary_10_1007_s11263_024_02281_7 crossref_primary_10_1016_j_knosys_2021_106832 crossref_primary_10_1109_TCSVT_2024_3411655 crossref_primary_10_1109_TIP_2020_2993406 crossref_primary_10_1109_ACCESS_2021_3073127 crossref_primary_10_1109_TCSVT_2021_3068985 crossref_primary_10_1109_TIM_2022_3204081 crossref_primary_10_1007_s11263_020_01428_6 crossref_primary_10_1109_TMM_2020_3013383 crossref_primary_10_1109_TCSVT_2021_3121012 crossref_primary_10_1007_s11263_020_01421_z crossref_primary_10_1109_TMM_2020_3019680 crossref_primary_10_1016_j_jvcir_2021_103133 crossref_primary_10_1109_TIP_2020_3000612 crossref_primary_10_1109_TMM_2024_3359480 crossref_primary_10_3390_app11030997 crossref_primary_10_1007_s00521_023_08899_x crossref_primary_10_1109_LSP_2020_2974691 crossref_primary_10_3390_s22134707 crossref_primary_10_1016_j_image_2023_116926 crossref_primary_10_1109_TGRS_2022_3142805 crossref_primary_10_1109_TIP_2020_2990606 crossref_primary_10_1109_TNNLS_2022_3227730 crossref_primary_10_1109_TIP_2020_2973802 crossref_primary_10_1109_TNNLS_2020_3015897 crossref_primary_10_1109_ACCESS_2020_3003126 crossref_primary_10_1109_TNNLS_2021_3071245 crossref_primary_10_1109_TIP_2022_3180561 crossref_primary_10_1007_s00530_024_01469_8 crossref_primary_10_1016_j_neucom_2022_02_059 crossref_primary_10_1109_TMM_2021_3127360 crossref_primary_10_1109_TPAMI_2023_3307666 crossref_primary_10_1109_TCI_2025_3527142 crossref_primary_10_3390_atmos12070828 crossref_primary_10_1007_s10489_022_03441_3 crossref_primary_10_1016_j_neucom_2021_06_052 crossref_primary_10_1109_TCSVT_2020_3024687 crossref_primary_10_1109_ACCESS_2020_3024542 crossref_primary_10_1016_j_image_2025_117311 crossref_primary_10_1016_j_image_2021_116460 crossref_primary_10_1109_TCSVT_2022_3207516 crossref_primary_10_1117_1_JEI_31_4_043003 crossref_primary_10_1109_ACCESS_2020_3034238 crossref_primary_10_1007_s41870_021_00742_7 crossref_primary_10_1049_ipr2_12347 crossref_primary_10_1109_TIP_2023_3335822 crossref_primary_10_1007_s10723_023_09684_9 crossref_primary_10_1016_j_knosys_2020_106000 crossref_primary_10_1049_ipr2_13258 crossref_primary_10_1145_3639407 crossref_primary_10_1109_TCSVT_2023_3246953 crossref_primary_10_1109_TPAMI_2020_2995190 crossref_primary_10_3390_s25030951 crossref_primary_10_1016_j_image_2020_115839 crossref_primary_10_1145_3625818 crossref_primary_10_1007_s10489_021_02485_1 crossref_primary_10_1109_ACCESS_2021_3072687 crossref_primary_10_1007_s11063_021_10486_x crossref_primary_10_1007_s11263_024_02250_0 crossref_primary_10_1109_TNNLS_2021_3112235 crossref_primary_10_1007_s00034_022_02279_x crossref_primary_10_1109_LSP_2020_2970345 crossref_primary_10_1016_j_neucom_2023_127066 crossref_primary_10_1109_TCSVT_2022_3229730 |
| Cites_doi | 10.1109/CVPR.2017.183 10.1109/CVPR.2017.243 10.1145/3123266.3127927 10.1109/CVPR.2017.19 10.1109/VCIP.2017.8305071 10.1109/ICIP.2013.6738189 10.1109/ICCV.2015.388 10.1109/TPAMI.2015.2439281 10.1109/DCC.2018.00066 10.1109/TMM.2013.2284759 10.1109/CVPR.2018.00854 10.1109/CVPR.2016.185 10.1109/ISCAS.2018.8351165 10.1109/TIP.2017.2708502 10.1109/ICCV.2017.517 10.1109/ICIP.2016.7532596 10.5121/ijma.2013.5402 10.1098/rsta.2015.0203 10.1109/34.192463 10.1109/TIP.2003.819861 10.1023/A:1016328200723 10.1016/j.apm.2018.03.001 10.1109/CVPR.2016.299 10.1109/MMSP.2012.6343435 10.1109/ICCV.2013.84 10.1109/ICPR.2018.8545729 10.1109/CVPR.2017.186 10.1109/TIP.2018.2882923 10.1109/TIP.2017.2750403 10.1109/TPAMI.2008.103 10.1109/ICIP.2014.7025909 10.1109/CVPR.2016.90 10.1109/ICCV.2017.191 10.1109/ICCV.2017.486 10.1007/s11042-018-5805-z 10.1109/DCC.2018.00021 10.1109/TIP.2016.2598681 10.1109/TIP.2017.2662206 10.1109/ICCV.2017.276 10.1109/WOCN.2013.6616235 10.1109/ICIP.2018.8451694 10.1109/ICCV.2009.5459440 10.1109/83.718489 10.1109/CVPR.2017.618 10.1049/el:20080522 10.1109/ICCV.2013.247 10.1109/TIP.2011.2179057 10.1109/CVPR.2012.6247661 10.1109/TCSVT.2017.2734838 10.1109/FG.2018.00118 10.1109/TIP.2017.2691802 10.1109/ICME.2012.92 10.1109/TIP.2018.2869722 10.1109/ICCV.2017.189 10.1016/j.cviu.2017.09.002 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TIP.2019.2892685 |
| 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 | PubMed Technology Research Database MEDLINE - Academic |
| 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 | 2961 |
| ExternalDocumentID | 30640610 10_1109_TIP_2019_2892685 8610325 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61772043 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Beijing Municipality grantid: L182002; 4192025 funderid: 10.13039/501100004826 – fundername: Nvidia funderid: 10.13039/100007065 |
| 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 RIG Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c347t-e5a72504ef4dcc028ced28982e8ec1d4bfa48d0a1434438ac2cb5f79ab27e7993 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 92 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000464920200007&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 | Thu Oct 02 17:58:50 EDT 2025 Mon Jun 30 10:20:57 EDT 2025 Wed Feb 19 02:09:32 EST 2025 Tue Nov 18 21:15:22 EST 2025 Sat Nov 29 03:21:09 EST 2025 Wed Aug 27 02:47:13 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| 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-e5a72504ef4dcc028ced28982e8ec1d4bfa48d0a1434438ac2cb5f79ab27e7993 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-1692-0069 0000-0002-5576-8629 0000-0002-4944-9621 0000-0002-0468-9576 |
| PMID | 30640610 |
| PQID | 2210039606 |
| PQPubID | 85429 |
| PageCount | 14 |
| ParticipantIDs | crossref_primary_10_1109_TIP_2019_2892685 crossref_citationtrail_10_1109_TIP_2019_2892685 proquest_miscellaneous_2179366108 proquest_journals_2210039606 ieee_primary_8610325 pubmed_primary_30640610 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-06-01 |
| PublicationDateYYYYMMDD | 2019-06-01 |
| PublicationDate_xml | – month: 06 year: 2019 text: 2019-06-01 day: 01 |
| PublicationDecade | 2010 |
| 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 | 2019 |
| 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 | ref57 ref13 ref12 ref59 ref58 ref14 ref53 ref52 ref55 ref54 ref10 wei (ref35) 2018 ref17 ref16 ref19 ref18 chen (ref11) 2013 ref46 ref45 zhang (ref15) 2018 ref48 gatys (ref30) 2015 ref42 ref41 ref44 yu (ref65) 2016 ref8 ref7 zhao (ref56) 2003; 2 ref4 ref3 ref6 ref5 li (ref9) 2017 ref40 zhang (ref49) 2018 ref34 ref37 ref36 ref31 ref74 ref32 dong (ref51) 2018 ref2 ref1 ref39 schuler (ref29) 2014 ref38 lore (ref33) 2015 zhang (ref47) 2018 ren (ref72) 2018 zhang (ref50) 2018 zhang (ref70) 2017 ref71 lai (ref26) 0 ref73 yang (ref23) 0 ref68 ref24 ref67 ref69 ref25 ref64 ref20 ref63 ref66 ref22 ref21 ref28 ref27 ref60 denton (ref62) 2015 ref61 hu (ref43) 2018 |
| References_xml | – start-page: 1 year: 2018 ident: ref50 article-title: Densely connected pyramid dehazing network publication-title: Proc IEEE Int Conf Comput Vis Pattern Recognit – ident: ref8 doi: 10.1109/CVPR.2017.183 – ident: ref45 doi: 10.1109/CVPR.2017.243 – ident: ref27 doi: 10.1145/3123266.3127927 – start-page: 2139 year: 2013 ident: ref11 article-title: Rain removal from dynamic scene based on motion segmentation publication-title: Proc IEEE Int Symp Circuits Syst (ISCAS) – year: 2017 ident: ref70 publication-title: Image De-raining Using a Conditional Generative Adversarial Network – ident: ref46 doi: 10.1109/CVPR.2017.19 – ident: ref28 doi: 10.1109/VCIP.2017.8305071 – start-page: 1 year: 2018 ident: ref15 article-title: Density-aware single image de-raining using a multi-stream dense network publication-title: Proc IEEE Int Conf Comput Vis Pattern Recognit – start-page: 1486 year: 2015 ident: ref62 article-title: Deep generative image models using a Laplacian pyramid of adversarial networks publication-title: Proc Annu Conf Neural Inf Process Syst – ident: ref14 doi: 10.1109/ICIP.2013.6738189 – ident: ref4 doi: 10.1109/ICCV.2015.388 – start-page: 1 year: 2018 ident: ref35 article-title: Deep retinex decomposition for low-light enhancement publication-title: Proc Brit Mach Vis Conf (BMVC) – ident: ref21 doi: 10.1109/TPAMI.2015.2439281 – ident: ref42 doi: 10.1109/DCC.2018.00066 – ident: ref2 doi: 10.1109/TMM.2013.2284759 – ident: ref53 doi: 10.1109/CVPR.2018.00854 – year: 2018 ident: ref51 publication-title: Joint demosaicing and denoising with perceptual optimization on a generative adversarial network – ident: ref71 doi: 10.1109/CVPR.2016.185 – start-page: 1 year: 2018 ident: ref43 article-title: Optimized recurrent network for intra prediction in video coding publication-title: Proc IEEE Vis Commun Image Process – ident: ref25 doi: 10.1109/ISCAS.2018.8351165 – start-page: 1 year: 2018 ident: ref72 article-title: Gated fusion network for single image dehazing publication-title: Proc IEEE Int Conf Comput Vis Pattern Recognit – start-page: 1 year: 2016 ident: ref65 article-title: Multi-scale context aggregation by dilated convolutions publication-title: Proc Int Conf Learn Represent – ident: ref19 doi: 10.1109/TIP.2017.2708502 – ident: ref52 doi: 10.1109/ICCV.2017.517 – ident: ref57 doi: 10.1109/ICIP.2016.7532596 – ident: ref55 doi: 10.5121/ijma.2013.5402 – ident: ref58 doi: 10.1098/rsta.2015.0203 – ident: ref64 doi: 10.1109/34.192463 – year: 2015 ident: ref33 publication-title: Llnet A deep autoencoder approach to natural low-light image enhancement – ident: ref74 doi: 10.1109/TIP.2003.819861 – ident: ref66 doi: 10.1023/A:1016328200723 – ident: ref69 doi: 10.1016/j.apm.2018.03.001 – ident: ref5 doi: 10.1109/CVPR.2016.299 – ident: ref12 doi: 10.1109/MMSP.2012.6343435 – ident: ref32 doi: 10.1109/ICCV.2013.84 – ident: ref61 doi: 10.1109/ICPR.2018.8545729 – ident: ref6 doi: 10.1109/CVPR.2017.186 – ident: ref40 doi: 10.1109/TIP.2018.2882923 – ident: ref22 doi: 10.1109/TIP.2017.2750403 – ident: ref54 doi: 10.1109/TPAMI.2008.103 – ident: ref3 doi: 10.1109/ICIP.2014.7025909 – ident: ref44 doi: 10.1109/CVPR.2016.90 – ident: ref16 doi: 10.1109/ICCV.2017.191 – start-page: 1 year: 2018 ident: ref49 article-title: Image super-resolution using very deep residual channel attention networks publication-title: Proc IEEE Int Conf Comput Vis – ident: ref48 doi: 10.1109/ICCV.2017.486 – year: 2015 ident: ref30 publication-title: A neural algorithm of artistic style – ident: ref39 doi: 10.1007/s11042-018-5805-z – ident: ref41 doi: 10.1109/DCC.2018.00021 – ident: ref31 doi: 10.1109/TIP.2016.2598681 – ident: ref20 doi: 10.1109/TIP.2017.2662206 – year: 2014 ident: ref29 publication-title: Learning to deblur – start-page: 1 year: 2018 ident: ref47 article-title: Residual dense network for image super-resolution publication-title: Proc IEEE Int Conf Comput Vis Pattern Recognit – ident: ref17 doi: 10.1109/ICCV.2017.276 – year: 0 ident: ref26 article-title: Fast and accurate image super-resolution with deep Laplacian pyramid networks publication-title: IEEE Trans Pattern Anal Mach Intell – year: 0 ident: ref23 article-title: Reference guided deep super-resolution via manifold localized external compensation publication-title: IEEE Trans Circuits Syst Video Technol – ident: ref59 doi: 10.1109/WOCN.2013.6616235 – ident: ref37 doi: 10.1109/ICIP.2018.8451694 – ident: ref67 doi: 10.1109/ICCV.2009.5459440 – volume: 2 start-page: ii-953 year: 2003 ident: ref56 article-title: Wavelet-domain HMT-based image super-resolution publication-title: Proc IEEE Int Conf Image Process – ident: ref60 doi: 10.1109/83.718489 – ident: ref63 doi: 10.1109/CVPR.2017.618 – ident: ref73 doi: 10.1049/el:20080522 – ident: ref13 doi: 10.1109/ICCV.2013.247 – year: 2017 ident: ref9 publication-title: Single image deraining using scale-aware multi-stage recurrent network – ident: ref1 doi: 10.1109/TIP.2011.2179057 – ident: ref68 doi: 10.1109/CVPR.2012.6247661 – ident: ref38 doi: 10.1109/TCSVT.2017.2734838 – ident: ref34 doi: 10.1109/FG.2018.00118 – ident: ref7 doi: 10.1109/TIP.2017.2691802 – ident: ref10 doi: 10.1109/ICME.2012.92 – ident: ref36 doi: 10.1109/TIP.2018.2869722 – ident: ref18 doi: 10.1109/ICCV.2017.189 – ident: ref24 doi: 10.1016/j.cviu.2017.09.002 |
| SSID | ssj0014516 |
| Score | 2.5696616 |
| Snippet | In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 2948 |
| SubjectTerms | Accumulation Adaptation models Degradation Image enhancement Rain Recovery recurrent process Redundancy residual dense network scale-free Single image deraining Testing Training Visibility wavelet transform Wavelet transforms |
| Title | Scale-Free Single Image Deraining Via Visibility-Enhanced Recurrent Wavelet Learning |
| URI | https://ieeexplore.ieee.org/document/8610325 https://www.ncbi.nlm.nih.gov/pubmed/30640610 https://www.proquest.com/docview/2210039606 https://www.proquest.com/docview/2179366108 |
| Volume | 28 |
| WOSCitedRecordID | wos000464920200007&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/eLvHCXMwlV1LT9wwEB7BikN7KM-2gQUZiUslzIass3aOVWEFF4RgoXuLHGfSItFstY9K_HtmHG_EoSBxiBQljmN5PPY3nvE3AEdJpZ3Jqpg0zRVSuSqTlhY6WaSqZO4T6wbOJ5vQV1dmPM6uV-C4PQuDiD74DE_41vvyy4lb8FZZzwyY_i1dhVWtB81ZrdZjwAlnvWcz1VIT7F-6JOOsN7q85hiu7ISMi2TAWZNfLEE-p8rr8NIvM8P19zVwAz4FOCm-N_LfhBWst2A9QEsRFHe2BR9f8A5uw-iWJINyOEUUt_TkEcXlH5pYxBmGjBHi_sHSFWJnn-R5_duHCogb3p9nRifx03LOirkIDK2_duBueD76cSFDegXp-krPJaZWM4EZVqp0jnAG1UI9ZBI06E5LVVRWmTK2hKiU6hvrEleklc5skWjUhGs-Q6ee1PgVhFYZWm1im6YlWYjWmIJ55PrWIVOinUbQW_Z47gL3OKfAeMy9DRJnOckoZxnlQUYRfGu_-NvwbrxRdptF0ZYLUoiguxRqHhRzlidk4sZ9NtsiOGxfk0qxn8TWOFlQGZ60CLfEJoIvzWBo62aDjSBQvPv_f-7BB25ZE0vWhc58usB9WHP_5g-z6QGN27E58OP2Ges-57o |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB1RQCo9lAKFBmhxpV6QajZknbVzrIAVK2CFYFu4RY4zKUiQRftRqf-eGa834tBW6iFSlDhO5PHHm8z4PYAvSaWdyaqYRporpHJVJi0tdLJIVcncJ9Z1nBeb0P2-ub3NLhfga7MXBhF98hke8KmP5ZdDN-VfZS3TYfq39BUssXJW2K3VxAxYctbHNlMtNQH_eVAyzlqD3iVncWUH5F4kHdZNfrEIeVWVvwNMv9B0V__vE9_B2wAoxbdZD1iDBazXYTWASxGG7ngd3rxgHtyAwTXZBmV3hCiu6coDit4jTS3iGINmhPhxb-kI2bO_5Ul955MFxBX_oWdOJ3FjWbViIgJH68_38L17Mjg6lUFgQbq20hOJqdVMYYaVKp0jpEG1UAuZBA26w1IVlVWmjC1hKqXaxrrEFWmlM1skGjUhm01YrIc1fgChVYZWm9imaUk-ojWmYCa5tnXIpGiHEbTmLZ67wD7OIhgPufdC4iwnG-VsozzYKIL95omnGfPGP8pusCmacsEKEezOjZqHoTnOE3Jy4zY7bhF8bm7ToOJIia1xOKUyPG0RcolNBFuzztDUzS4bgaB4-8_v3IPXp4OL8_y81z_bgRX-yllm2S4sTkZT_AjL7tfkfjz65HvvM6196hs |
| 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=Scale-Free+Single+Image+Deraining+Via+Visibility-Enhanced+Recurrent+Wavelet+Learning&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Yang%2C+Wenhan&rft.au=Liu%2C+Jiaying&rft.au=Yanga%2C+Shuai&rft.au=Guo%2C+Zongming&rft.date=2019-06-01&rft.issn=1941-0042&rft.eissn=1941-0042&rft_id=info:doi/10.1109%2FTIP.2019.2892685&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 |