Rain-Free and Residue Hand-in-Hand: A Progressive Coupled Network for Real-Time Image Deraining
Rainy weather is a challenge for many vision-oriented tasks ( e.g. , object detection and segmentation), which causes performance degradation. Image deraining is an effective solution to avoid performance drop of downstream vision tasks. However, most existing deraining methods either fail to produc...
Uloženo v:
| Vydáno v: | IEEE transactions on image processing Ročník 30; s. 7404 - 7418 |
|---|---|
| Hlavní autoři: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
New York
IEEE
2021
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 | Rainy weather is a challenge for many vision-oriented tasks ( e.g. , object detection and segmentation), which causes performance degradation. Image deraining is an effective solution to avoid performance drop of downstream vision tasks. However, most existing deraining methods either fail to produce satisfactory restoration results or cost too much computation. In this work, considering both effectiveness and efficiency of image deraining, we propose a progressive coupled network (PCNet) to well separate rain streaks while preserving rain-free details. To this end, we investigate the blending correlations between them and particularly devise a novel coupled representation module (CRM) to learn the joint features and the blending correlations. By cascading multiple CRMs, PCNet extracts the hierarchical features of multi-scale rain streaks, and separates the rain-free content and rain streaks progressively. To promote computation efficiency, we employ depth-wise separable convolutions and a U-shaped structure, and construct CRM in an asymmetric architecture to reduce model parameters and memory footprint. Extensive experiments are conducted to evaluate the efficacy of the proposed PCNet in two aspects: (1) image deraining on several synthetic and real-world rain datasets and (2) joint image deraining and downstream vision tasks ( e.g. , object detection and segmentation). Furthermore, we show that the proposed CRM can be easily adopted to similar image restoration tasks including image dehazing and low-light enhancement with competitive performance. The source code is available at https://github.com/kuijiang0802/PCNet . |
|---|---|
| AbstractList | Rainy weather is a challenge for many vision-oriented tasks ( e.g. , object detection and segmentation), which causes performance degradation. Image deraining is an effective solution to avoid performance drop of downstream vision tasks. However, most existing deraining methods either fail to produce satisfactory restoration results or cost too much computation. In this work, considering both effectiveness and efficiency of image deraining, we propose a progressive coupled network (PCNet) to well separate rain streaks while preserving rain-free details. To this end, we investigate the blending correlations between them and particularly devise a novel coupled representation module (CRM) to learn the joint features and the blending correlations. By cascading multiple CRMs, PCNet extracts the hierarchical features of multi-scale rain streaks, and separates the rain-free content and rain streaks progressively. To promote computation efficiency, we employ depth-wise separable convolutions and a U-shaped structure, and construct CRM in an asymmetric architecture to reduce model parameters and memory footprint. Extensive experiments are conducted to evaluate the efficacy of the proposed PCNet in two aspects: (1) image deraining on several synthetic and real-world rain datasets and (2) joint image deraining and downstream vision tasks ( e.g. , object detection and segmentation). Furthermore, we show that the proposed CRM can be easily adopted to similar image restoration tasks including image dehazing and low-light enhancement with competitive performance. The source code is available at https://github.com/kuijiang0802/PCNet . Rainy weather is a challenge for many vision-oriented tasks (e.g., object detection and segmentation), which causes performance degradation. Image deraining is an effective solution to avoid performance drop of downstream vision tasks. However, most existing deraining methods either fail to produce satisfactory restoration results or cost too much computation. In this work, considering both effectiveness and efficiency of image deraining, we propose a progressive coupled network (PCNet) to well separate rain streaks while preserving rain-free details. To this end, we investigate the blending correlations between them and particularly devise a novel coupled representation module (CRM) to learn the joint features and the blending correlations. By cascading multiple CRMs, PCNet extracts the hierarchical features of multi-scale rain streaks, and separates the rain-free content and rain streaks progressively. To promote computation efficiency, we employ depth-wise separable convolutions and a U-shaped structure, and construct CRM in an asymmetric architecture to reduce model parameters and memory footprint. Extensive experiments are conducted to evaluate the efficacy of the proposed PCNet in two aspects: (1) image deraining on several synthetic and real-world rain datasets and (2) joint image deraining and downstream vision tasks (e.g., object detection and segmentation). Furthermore, we show that the proposed CRM can be easily adopted to similar image restoration tasks including image dehazing and low-light enhancement with competitive performance. The source code is available at https://github.com/kuijiang0802/PCNet.Rainy weather is a challenge for many vision-oriented tasks (e.g., object detection and segmentation), which causes performance degradation. Image deraining is an effective solution to avoid performance drop of downstream vision tasks. However, most existing deraining methods either fail to produce satisfactory restoration results or cost too much computation. In this work, considering both effectiveness and efficiency of image deraining, we propose a progressive coupled network (PCNet) to well separate rain streaks while preserving rain-free details. To this end, we investigate the blending correlations between them and particularly devise a novel coupled representation module (CRM) to learn the joint features and the blending correlations. By cascading multiple CRMs, PCNet extracts the hierarchical features of multi-scale rain streaks, and separates the rain-free content and rain streaks progressively. To promote computation efficiency, we employ depth-wise separable convolutions and a U-shaped structure, and construct CRM in an asymmetric architecture to reduce model parameters and memory footprint. Extensive experiments are conducted to evaluate the efficacy of the proposed PCNet in two aspects: (1) image deraining on several synthetic and real-world rain datasets and (2) joint image deraining and downstream vision tasks (e.g., object detection and segmentation). Furthermore, we show that the proposed CRM can be easily adopted to similar image restoration tasks including image dehazing and low-light enhancement with competitive performance. The source code is available at https://github.com/kuijiang0802/PCNet. |
| Author | Lin, Chia-Wen Chen, Chen Yi, Peng Wang, Zheng Jiang, Kui Wang, Xiao Jiang, Junjun Wang, Zhongyuan |
| Author_xml | – sequence: 1 givenname: Kui orcidid: 0000-0002-4055-7503 surname: Jiang fullname: Jiang, Kui email: kuijiang_1994@163.com organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China – sequence: 2 givenname: Zhongyuan orcidid: 0000-0002-9796-488X surname: Wang fullname: Wang, Zhongyuan email: wzy_hope@163.com organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China – sequence: 3 givenname: Peng orcidid: 0000-0001-9366-951X surname: Yi fullname: Yi, Peng email: yipeng@whu.edu.cn organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China – sequence: 4 givenname: Chen orcidid: 0000-0003-3957-7061 surname: Chen fullname: Chen, Chen email: chen.chen@ucf.edu organization: Center for Research in Computer Vision (CRCV), University of Central Florida, Orlando, FL, USA – sequence: 5 givenname: Zheng orcidid: 0000-0003-3846-9157 surname: Wang fullname: Wang, Zheng email: wangzwhu@whu.edu.cn organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China – sequence: 6 givenname: Xiao surname: Wang fullname: Wang, Xiao email: hebeiwangxiao@163.com organization: National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China – sequence: 7 givenname: Junjun orcidid: 0000-0002-5694-505X surname: Jiang fullname: Jiang, Junjun email: junjun0595@163.com organization: Peng Cheng Laboratory, Shenzhen, China – sequence: 8 givenname: Chia-Wen orcidid: 0000-0002-9097-2318 surname: Lin fullname: Lin, Chia-Wen email: cwlin@ee.nthu.edu.tw organization: Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan |
| BookMark | eNp9kEtrGzEURkVwyLP7QjeCbroZ9-o1j-6Mm4chJCG4a6HR3DFKxyNXmknpv48Gmyy86OpK6DvfFeeSzHrfIyGfGcwZg-r7evU858DZXDDgCuQJuWCVZBmA5LN0BlVkBZPVObmM8RWAScXyM3IupAQhRH5B9ItxfXYbEKnpG_qC0TUj0vt0ydLDNH_QBX0OfhMwRveGdOnHXYcNfcThrw-_aetD4kyXrd0W6WprNkh_Yki9rt9ck9PWdBE_HeYV-XV7s17eZw9Pd6vl4iGzgsshqxlDLqtSWgsKc9OKsinrumhsW0MNDKCtbdOWoqwKLJqy5XVRS0CW20oUKMUV-bbv3QX_Z8Q46K2LFrvO9OjHqLnKueIgoEzRr0fRVz-GPv1uSikuCiWnQtinbPAxBmz1LritCf80Az3J10m-nuTrg_yE5EeIdYMZnO-HZKP7H_hlDzpE_NhTKaZUycU7Po-Pqw |
| CODEN | IIPRE4 |
| CitedBy_id | crossref_primary_10_1109_TPAMI_2023_3238179 crossref_primary_10_3390_electronics11091375 crossref_primary_10_1007_s00530_024_01606_3 crossref_primary_10_1109_TIP_2025_3567205 crossref_primary_10_1109_TMM_2024_3521760 crossref_primary_10_1109_TBDATA_2024_3442538 crossref_primary_10_3390_w15081585 crossref_primary_10_1109_TETCI_2024_3382233 crossref_primary_10_1007_s11760_025_04723_2 crossref_primary_10_1016_j_neucom_2024_129236 crossref_primary_10_1049_ipr2_12726 crossref_primary_10_1080_19479832_2025_2465532 crossref_primary_10_1109_TMM_2024_3387746 crossref_primary_10_1109_TMM_2024_3366765 crossref_primary_10_1109_TIP_2023_3334556 crossref_primary_10_1016_j_eswa_2025_126857 crossref_primary_10_1145_3689642 crossref_primary_10_3390_electronics11091384 crossref_primary_10_1145_3679203 crossref_primary_10_1109_LSP_2024_3407536 crossref_primary_10_1109_ACCESS_2024_3508805 crossref_primary_10_1016_j_dsp_2022_103740 crossref_primary_10_1109_LGRS_2021_3112038 crossref_primary_10_1007_s00371_024_03287_5 crossref_primary_10_1016_j_cviu_2025_104287 crossref_primary_10_1007_s11760_021_02046_6 crossref_primary_10_1109_TGRS_2023_3347745 crossref_primary_10_3390_math11030691 crossref_primary_10_1016_j_jvcir_2024_104250 crossref_primary_10_1016_j_neucom_2022_02_059 crossref_primary_10_1007_s11063_024_11541_z crossref_primary_10_1016_j_inffus_2025_103104 crossref_primary_10_1109_TETCI_2024_3369321 crossref_primary_10_1080_10095020_2023_2288179 crossref_primary_10_1016_j_jvcir_2022_103719 crossref_primary_10_1007_s11042_023_17146_3 crossref_primary_10_1049_ipr2_70040 crossref_primary_10_1016_j_geits_2025_100337 crossref_primary_10_1109_LSP_2021_3129667 crossref_primary_10_1007_s11227_022_04895_5 crossref_primary_10_1016_j_jestch_2024_101893 crossref_primary_10_3390_electronics11091354 crossref_primary_10_1109_ACCESS_2024_3407750 crossref_primary_10_1109_TMM_2025_3535316 crossref_primary_10_1109_TCE_2024_3409313 crossref_primary_10_1109_LSP_2023_3330129 crossref_primary_10_1109_ACCESS_2024_3392016 crossref_primary_10_1016_j_neucom_2023_127066 crossref_primary_10_1016_j_eswa_2025_128308 crossref_primary_10_1016_j_dsp_2025_105216 crossref_primary_10_1016_j_eswa_2024_126248 crossref_primary_10_3390_electronics11091298 crossref_primary_10_1109_TCSVT_2024_3411655 crossref_primary_10_1016_j_dsp_2023_104248 crossref_primary_10_1109_TIP_2023_3272173 crossref_primary_10_1117_1_JEI_32_6_063015 crossref_primary_10_1016_j_neucom_2022_04_034 crossref_primary_10_1109_TNNLS_2025_3527557 crossref_primary_10_1016_j_engappai_2025_110267 crossref_primary_10_1109_LSP_2024_3374057 crossref_primary_10_1007_s11760_023_02649_1 crossref_primary_10_1016_j_infrared_2024_105390 crossref_primary_10_1109_LSP_2025_3577924 crossref_primary_10_1007_s00521_023_08899_x crossref_primary_10_3390_s24206724 crossref_primary_10_3390_s22134707 crossref_primary_10_3390_sym15081571 crossref_primary_10_1109_TCSVT_2024_3469190 crossref_primary_10_1007_s44267_025_00083_0 crossref_primary_10_3390_app13042709 crossref_primary_10_1109_TCSVT_2023_3264824 crossref_primary_10_1109_JSEN_2024_3350742 crossref_primary_10_1016_j_patcog_2023_110205 crossref_primary_10_1016_j_engappai_2023_107789 crossref_primary_10_1109_LSP_2021_3118640 crossref_primary_10_1007_s11431_023_2614_8 crossref_primary_10_1109_TGRS_2023_3277486 crossref_primary_10_1109_TCSVT_2024_3377365 crossref_primary_10_1007_s00530_024_01469_8 crossref_primary_10_1109_TMM_2022_3144066 crossref_primary_10_1109_TPAMI_2024_3525089 crossref_primary_10_1016_j_knosys_2025_113162 crossref_primary_10_1016_j_inffus_2024_102494 crossref_primary_10_1016_j_neucom_2025_129490 crossref_primary_10_1177_1088467X241308764 crossref_primary_10_1007_s00530_024_01462_1 crossref_primary_10_1109_TVCG_2025_3550844 crossref_primary_10_1007_s11263_024_02056_0 crossref_primary_10_1109_LSP_2024_3383796 crossref_primary_10_1109_TGRS_2022_3215205 crossref_primary_10_1109_ACCESS_2024_3480205 crossref_primary_10_1016_j_engappai_2024_109067 crossref_primary_10_1016_j_image_2025_117311 crossref_primary_10_1109_TIM_2022_3230482 crossref_primary_10_1007_s00371_022_02533_y crossref_primary_10_1016_j_eswa_2023_121339 crossref_primary_10_1049_ipr2_12669 crossref_primary_10_1007_s10044_024_01401_w crossref_primary_10_1109_JSEN_2023_3263834 crossref_primary_10_1016_j_jvcir_2024_104060 crossref_primary_10_1109_JAS_2024_124521 crossref_primary_10_1109_LSP_2022_3154981 crossref_primary_10_3390_ai5040113 crossref_primary_10_3390_electronics13163182 crossref_primary_10_1109_TCE_2025_3534680 crossref_primary_10_1109_TGRS_2023_3291822 crossref_primary_10_1109_TPAMI_2025_3584921 crossref_primary_10_1016_j_cviu_2024_104097 crossref_primary_10_1109_TMM_2022_3141886 crossref_primary_10_1016_j_patcog_2025_112081 crossref_primary_10_1080_17538947_2025_2480267 crossref_primary_10_1109_TNNLS_2021_3112235 crossref_primary_10_1109_TCSVT_2022_3229730 |
| Cites_doi | 10.1109/CVPR.2019.00060 10.1109/TIP.2020.3048625 10.1109/TCSVT.2017.2748150 10.1007/978-3-030-01234-2_16 10.1016/j.cviu.2019.05.003 10.1145/3240508.3240636 10.1007/s11263-020-01421-z 10.1109/CVPR42600.2020.00597 10.1609/aaai.v34i07.6706 10.1109/TPAMI.2020.2995190 10.1145/3343031.3350926 10.1109/ICCV.2017.511 10.1007/978-3-642-33715-4_54 10.1109/CVPR.2018.00194 10.1109/TIP.2018.2867951 10.1109/TCSVT.2018.2880223 10.1109/TCSVT.2020.3044887 10.1109/CVPR.2018.00716 10.1007/s11263-020-01428-6 10.1109/TMM.2013.2284759 10.1109/CVPR.2019.00701 10.1007/978-3-642-33266-1_8 10.1109/CVPR42600.2020.00313 10.1109/TIP.2006.877407 10.1109/TIP.2021.3051462 10.1109/CVPR42600.2020.00324 10.1109/ICCVW.2017.71 10.1109/TPAMI.2020.3042298 10.1109/TIP.2017.2691802 10.1609/aaai.v34i07.6865 10.1109/CVPR.2017.618 10.1109/CVPR.2018.00132 10.1109/CVPR.2019.00941 10.1515/9783110524116 10.1109/TIP.2021.3064229 10.1109/CVPR42600.2020.00288 10.1609/aaai.v34i07.6701 10.1109/WACV.2017.145 10.1109/CVPR.2019.00835 10.1109/83.557356 10.1109/ICCV.2017.322 10.1109/CVPR.2018.00068 10.1007/s11263-020-01416-w 10.1109/TPAMI.2015.2439281 10.1109/TIP.2011.2179057 10.1109/TCSVT.2019.2920407 10.1109/ICCV.2005.253 10.1109/CVPR.2019.00821 10.1109/CVPR.2017.549 10.1016/j.image.2014.06.006 10.1109/CVPR42600.2020.00837 10.1109/CVPR.2017.186 10.1109/CVPR.2019.00396 10.1109/CVPR.2019.00860 10.1109/LSP.2012.2227726 10.1109/ICCV.2019.00200 10.1109/CVPR.2019.00406 10.1109/TIP.2016.2639450 10.1109/CVPR.2019.00400 10.1109/CVPR.2018.00079 10.1109/TIP.2006.881969 10.1109/TNNLS.2019.2926481 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TIP.2021.3102504 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef 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 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 |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 2 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 | 7418 |
| ExternalDocumentID | 10_1109_TIP_2021_3102504 9515582 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Hubei Technological Innovation Special Fund; Hubei Province Technological Innovation Major Project grantid: 2020BAB018 funderid: 10.13039/501100012239 – fundername: National Natural Science Foundation of China grantid: U1903214; 62071339; 61971165; 61671332; 61801335 funderid: 10.13039/501100001809 – fundername: Qualcomm Technologies, Inc., USA, through the Taiwan University Research Collaboration Project grantid: NAT-410478 funderid: 10.13039/100005144 |
| 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 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c324t-b11e24984cc05e6af38d8bb7dcfb0b0100fbcdf83897e7d8f2b7b40e16c937e43 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 148 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000690439600004&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 | Wed Oct 01 13:05:27 EDT 2025 Mon Jun 30 10:19:52 EDT 2025 Tue Nov 18 21:25:32 EST 2025 Sat Nov 29 03:21:15 EST 2025 Wed Aug 27 02:27:36 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-c324t-b11e24984cc05e6af38d8bb7dcfb0b0100fbcdf83897e7d8f2b7b40e16c937e43 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-9366-951X 0000-0002-4055-7503 0000-0003-3957-7061 0000-0002-5694-505X 0000-0002-9097-2318 0000-0003-3846-9157 0000-0002-9796-488X |
| PMID | 34403336 |
| PQID | 2565237544 |
| PQPubID | 85429 |
| PageCount | 15 |
| ParticipantIDs | crossref_primary_10_1109_TIP_2021_3102504 crossref_citationtrail_10_1109_TIP_2021_3102504 proquest_miscellaneous_2562520308 proquest_journals_2565237544 ieee_primary_9515582 |
| PublicationCentury | 2000 |
| PublicationDate | 20210000 2021-00-00 20210101 |
| PublicationDateYYYYMMDD | 2021-01-01 |
| PublicationDate_xml | – year: 2021 text: 20210000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on image processing |
| PublicationTitleAbbrev | TIP |
| PublicationYear | 2021 |
| 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 ref56 ref12 ioffe (ref28) 2015 ref59 ref15 ref58 krizhevsky (ref27) 2012 ref55 ref54 ref10 yang (ref23) 2021 he (ref84) 2020; 12358 ref17 ref16 ref19 ref18 guo (ref82) 2020 feifan lv (ref79) 2018 wang (ref52) 2019 redmon (ref66) 2018 ref46 ref45 yu (ref70) 2018 ref47 ref42 ref85 ref41 ref44 ref43 ref8 ref7 zamir (ref51) 2020 ref9 ref4 ref3 ref6 wei (ref71) 2018 ref5 jiang (ref48) 2021 howard (ref29) 2017 ref81 ref40 ref83 zhang (ref49) 2019 mei (ref50) 2020 ref80 mehta (ref32) 2018 ref78 ref37 ref75 ref31 ref74 ref30 ding (ref63) 2020 ref77 ref33 ref76 ref2 sifre (ref35) 2014; 1 ref1 ref39 ref38 ding (ref34) 2021 ref73 ref72 eboli (ref36) 2020 ref68 ref24 ref67 ref26 ref69 ref25 li (ref14) 2017 ref64 ref20 ref22 ref65 ref21 zhang (ref53) 2018 ronneberger (ref11) 2015 ref60 ref62 ref61 |
| References_xml | – ident: ref10 doi: 10.1109/CVPR.2019.00060 – ident: ref16 doi: 10.1109/TIP.2020.3048625 – ident: ref44 doi: 10.1109/TCSVT.2017.2748150 – ident: ref5 doi: 10.1007/978-3-030-01234-2_16 – ident: ref8 doi: 10.1016/j.cviu.2019.05.003 – ident: ref19 doi: 10.1145/3240508.3240636 – ident: ref22 doi: 10.1007/s11263-020-01421-z – year: 2017 ident: ref14 article-title: Single image deraining using scale-aware multi-stage recurrent network publication-title: arXiv 1712 06830 – ident: ref45 doi: 10.1109/CVPR42600.2020.00597 – ident: ref37 doi: 10.1609/aaai.v34i07.6706 – ident: ref25 doi: 10.1109/TPAMI.2020.2995190 – year: 2021 ident: ref34 article-title: RepVGG: Making VGG-style ConvNets great again publication-title: arXiv 2101 03697 – ident: ref83 doi: 10.1145/3343031.3350926 – ident: ref72 doi: 10.1109/ICCV.2017.511 – ident: ref78 doi: 10.1007/978-3-642-33715-4_54 – ident: ref62 doi: 10.1109/CVPR.2018.00194 – start-page: 1097 year: 2012 ident: ref27 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst (NIPS) – year: 2020 ident: ref36 article-title: Structured and localized image restoration publication-title: arXiv 2006 09261 – ident: ref77 doi: 10.1109/TIP.2018.2867951 – start-page: 552 year: 2018 ident: ref32 article-title: Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation publication-title: Proc ECCV – ident: ref43 doi: 10.1109/TCSVT.2018.2880223 – start-page: 286 year: 2018 ident: ref53 article-title: Image super-resolution using very deep residual channel attention networks publication-title: Proc ECCV – year: 2017 ident: ref29 article-title: MobileNets: Efficient convolutional neural networks for mobile vision applications publication-title: arXiv 1704 04861 – ident: ref56 doi: 10.1109/TCSVT.2020.3044887 – ident: ref31 doi: 10.1109/CVPR.2018.00716 – ident: ref21 doi: 10.1007/s11263-020-01428-6 – ident: ref13 doi: 10.1109/TMM.2013.2284759 – year: 2020 ident: ref63 article-title: Image quality assessment: Unifying structure and texture similarity publication-title: arXiv 2004 07728 – year: 2021 ident: ref23 article-title: End-toend rain removal network based on progressive residual detail supplement publication-title: IEEE Trans Multimedia – ident: ref81 doi: 10.1109/CVPR.2019.00701 – ident: ref26 doi: 10.1007/978-3-642-33266-1_8 – ident: ref46 doi: 10.1109/CVPR42600.2020.00313 – ident: ref39 doi: 10.1109/TIP.2006.877407 – ident: ref47 doi: 10.1109/TIP.2021.3051462 – ident: ref38 doi: 10.1109/CVPR42600.2020.00324 – ident: ref30 doi: 10.1109/ICCVW.2017.71 – volume: 1 start-page: 3 year: 2014 ident: ref35 article-title: Rigid-motion scattering for image classification – ident: ref55 doi: 10.1109/TPAMI.2020.3042298 – start-page: 220 year: 2018 ident: ref79 article-title: MBLLEN: Low-light image/video enhancement using CNNs publication-title: Proc BMVC – volume: 12358 start-page: 679 year: 2020 ident: ref84 article-title: Conditional sequential modulation for efficient global image retouching publication-title: Proc ECCV – start-page: 234 year: 2015 ident: ref11 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Conf Med Image Comput Comput -Assist Intervent – ident: ref4 doi: 10.1109/TIP.2017.2691802 – ident: ref75 doi: 10.1609/aaai.v34i07.6865 – ident: ref54 doi: 10.1109/CVPR.2017.618 – ident: ref69 doi: 10.1109/CVPR.2018.00132 – ident: ref7 doi: 10.1109/CVPR.2019.00941 – start-page: 1 year: 2019 ident: ref49 article-title: Residual non-local attention networks for image restoration publication-title: Proc ICLR – start-page: 155 year: 2018 ident: ref71 article-title: Deep retinex decomposition for low-light enhancement publication-title: Proc BMVC – year: 2018 ident: ref66 article-title: YOLOv3: An incremental improvement publication-title: arXiv 1804 02767 – year: 2019 ident: ref52 article-title: An effective two-branch model-based deep network for single image deraining publication-title: arXiv 1905 05404 – ident: ref42 doi: 10.1515/9783110524116 – ident: ref20 doi: 10.1109/TIP.2021.3064229 – ident: ref74 doi: 10.1109/CVPR42600.2020.00288 – ident: ref76 doi: 10.1609/aaai.v34i07.6701 – ident: ref15 doi: 10.1109/WACV.2017.145 – ident: ref73 doi: 10.1109/CVPR.2019.00835 – year: 2021 ident: ref48 article-title: Degrade is upgrade: Learning degradation for low-light image enhancement publication-title: arXiv 2103 10621 – year: 2018 ident: ref70 article-title: BDD100K: A diverse driving dataset for heterogeneous multitask learning publication-title: arXiv 1805 04687 – ident: ref85 doi: 10.1109/83.557356 – ident: ref67 doi: 10.1109/ICCV.2017.322 – ident: ref61 doi: 10.1109/CVPR.2018.00068 – ident: ref24 doi: 10.1007/s11263-020-01416-w – start-page: 1777 year: 2020 ident: ref82 article-title: Zero-reference deep curve estimation for low-light image enhancement publication-title: Proc CVPR – ident: ref40 doi: 10.1109/TPAMI.2015.2439281 – ident: ref12 doi: 10.1109/TIP.2011.2179057 – ident: ref59 doi: 10.1109/TCSVT.2019.2920407 – ident: ref3 doi: 10.1109/ICCV.2005.253 – ident: ref65 doi: 10.1109/CVPR.2019.00821 – start-page: 448 year: 2015 ident: ref28 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proc ICML – ident: ref68 doi: 10.1109/CVPR.2017.549 – ident: ref58 doi: 10.1016/j.image.2014.06.006 – ident: ref1 doi: 10.1109/CVPR42600.2020.00837 – ident: ref17 doi: 10.1109/CVPR.2017.186 – ident: ref60 doi: 10.1109/CVPR.2019.00396 – ident: ref6 doi: 10.1109/CVPR.2019.00860 – ident: ref57 doi: 10.1109/LSP.2012.2227726 – ident: ref33 doi: 10.1109/ICCV.2019.00200 – start-page: 492 year: 2020 ident: ref51 article-title: Learning enriched features for real image restoration and enhancement publication-title: Proc ECCV – ident: ref2 doi: 10.1109/CVPR.2019.00406 – year: 2020 ident: ref50 article-title: Pyramid attention networks for image restoration publication-title: arXiv 2004 13824 – ident: ref80 doi: 10.1109/TIP.2016.2639450 – ident: ref64 doi: 10.1109/CVPR.2019.00400 – ident: ref18 doi: 10.1109/CVPR.2018.00079 – ident: ref41 doi: 10.1109/TIP.2006.881969 – ident: ref9 doi: 10.1109/TNNLS.2019.2926481 |
| SSID | ssj0014516 |
| Score | 2.6708088 |
| Snippet | Rainy weather is a challenge for many vision-oriented tasks ( e.g. , object detection and segmentation), which causes performance degradation. Image deraining... Rainy weather is a challenge for many vision-oriented tasks (e.g., object detection and segmentation), which causes performance degradation. Image deraining is... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 7404 |
| SubjectTerms | attention mechanism Blending Computational modeling Customer relationship management Degradation Feature extraction Image degradation Image deraining Image enhancement Image restoration Image segmentation multi-scale fusion non-local network Object recognition Performance degradation Production methods Rain Source code Task analysis Vision |
| Title | Rain-Free and Residue Hand-in-Hand: A Progressive Coupled Network for Real-Time Image Deraining |
| URI | https://ieeexplore.ieee.org/document/9515582 https://www.proquest.com/docview/2565237544 https://www.proquest.com/docview/2562520308 |
| Volume | 30 |
| WOSCitedRecordID | wos000690439600004&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/eLvHCXMwlV3fb9MwED6NCaHxwGAD0TEmI_GChKmTuLXD2zSotpeqQkPqW2Q7FwmppFPb7O_fneMGJBAST0nkH4lyZ_v7fOc7gPdWE841TZCNK1Fq65x0TYbSeGVd7k3mdYjJJsx8bpfLcnEAH4ezMIgYnc_wE99GW369Dh1vlY1LzkdiacJ9ZMy0P6s1WAw44Wy0bE6MNAT79yZJVY5vbxZEBPOM-GmM2HUETwqtVVHEuMy_VqOYXuWPOTkuNLPj__vE5_AsAUpx2WvACzjA9gSOE7gUaehuT-Dpb5EHT6Fiu46cbRCFa2vxDUkpOxTX9CCpgK-fxaVYsPcWO8reo7had3cr6nLeO44LQrvUzq0knyIRNz9pYhJfMGWceAnfZ19vr65lyrUgA0GqnfRZhsTErA5BTXDqmsLW1ntTh8bzXqlSjQ91YwnfGDS1bUiOXivMpoEADuriFRy26xZfg_Ch8DmRbkusW2cKnfU0G0-JaIXcTOp6BOP9P69CCkTO-TBWVSQkqqxIYBULrEoCG8GHocVdH4TjH3VPWSpDvSSQEZzvxVqlUbqtCO4RD-cQgCN4NxTT-GKjiWtx3cU6-STnqD5nf-_5DRzx-_ttmXM43G06fAuPw_3ux3ZzQaq6tBdRVR8AV2vh3g |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED5NA8F4YLCBKAwwEi9IeHUSp3b2Ng2qVoyqQkXam2U7FwmppFPb7O_n7KQBiWnSnpLIP2Tl7PP3-c53AB-1JJyrKs8rWyCX2lpuqwS5ckLb1KnESR-TTajZTF9dFfM9-NzfhUHE6HyGp-E12vLLlW_CUdmwCPlINCncB7mUqWhva_U2g5ByNto2c8UVAf-dUVIUw8V0TlQwTYihxphdB_Aok1JkWYzM_Hc_iglW_tPKcasZH95vkM_gaQcp2Xk7B57DHtZHcNjBS9Yt3s0RPPkn9uAxmGDZ4eM1IrN1yX4gTcsG2YQ-OBWE5xk7Z_PgvxVcZW-QXaya6yV1OWtdxxnhXWpnlzzcI2HT36Sa2Bfsck68gJ_jr4uLCe-yLXBPoGrLXZIgcTEtvRc5jmyV6VI7p0pfuXBaKkTlfFlpQjgKVakrkqSTApORJ4iDMnsJ-_WqxlfAnM9cSrRbE--WiUCrHenjEVEtn6q8LAcw3P1z47tQ5CEjxtJESiIKQwIzQWCmE9gAPvUtrtswHHfUPQ5S6et1AhnAyU6splunG0OAj5h4CAI4gA99Ma2wYDaxNa6aWCfN0xDX5_XtPb-Hx5PF90tzOZ19ewMHYSztIc0J7G_XDb6Fh_5m-2uzfhcn7B_taeQ9 |
| 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=Rain-Free+and+Residue+Hand-in-Hand%3A+A+Progressive+Coupled+Network+for+Real-Time+Image+Deraining&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Jiang%2C+Kui&rft.au=Wang%2C+Zhongyuan&rft.au=Yi%2C+Peng&rft.au=Chen%2C+Chen&rft.date=2021&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=30&rft.spage=7404&rft.epage=7418&rft_id=info:doi/10.1109%2FTIP.2021.3102504&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2021_3102504 |
| 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 |