MC-Blur: A Comprehensive Benchmark for Image Deblurring
Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods per...
Saved in:
| Published in | IEEE transactions on circuits and systems for video technology Vol. 34; no. 5; pp. 3755 - 3767 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
IEEE
01.05.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1051-8215 1558-2205 |
| DOI | 10.1109/TCSVT.2023.3319330 |
Cover
| Abstract | Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods perform in the case of multiple types of blur. For in-depth performance evaluation, we construct a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors. The images in the proposed MC-Blur dataset are collected using other techniques: averaging sharp images captured by a 1000-fps high-speed camera, convolving Ultra-High-Definition (UHD) sharp images with large-size kernels, adding defocus to images, and real-world blurry images captured by various camera models. Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset's capacity. These benchmarking results provide a comprehensive overview of the advantages and limitations of current deblurring methods, revealing our dataset's advances. The dataset is available to the public at https://github.com/HDCVLab/MC-Blur-Dataset . |
|---|---|
| AbstractList | Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods perform in the case of multiple types of blur. For in-depth performance evaluation, we construct a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors. The images in the proposed MC-Blur dataset are collected using other techniques: averaging sharp images captured by a 1000-fps high-speed camera, convolving Ultra-High-Definition (UHD) sharp images with large-size kernels, adding defocus to images, and real-world blurry images captured by various camera models. Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity. These benchmarking results provide a comprehensive overview of the advantages and limitations of current deblurring methods, revealing our dataset’s advances. The dataset is available to the public at https://github.com/HDCVLab/MC-Blur-Dataset . |
| Author | Stenger, Bjorn Liu, Wei Ren, Wenqi Zhang, Kaihao Luo, Wenhan Li, Hongdong Yang, Ming-Hsuan Wang, Tao |
| Author_xml | – sequence: 1 givenname: Kaihao orcidid: 0000-0002-4317-660X surname: Zhang fullname: Zhang, Kaihao email: kaihao.zhang@anu.edu.au organization: College of Engineering and Computer Science, The Australian National University, Canberra, Australia – sequence: 2 givenname: Tao orcidid: 0000-0002-0202-0174 surname: Wang fullname: Wang, Tao email: taowangzj@gmail.com organization: State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China – sequence: 3 givenname: Wenhan orcidid: 0000-0002-5697-4168 surname: Luo fullname: Luo, Wenhan email: whluo.china@gmail.com organization: School of Cyber Science and Technology, Sun Yat-sen University, Guangzhou, China – sequence: 4 givenname: Wenqi orcidid: 0000-0001-5481-653X surname: Ren fullname: Ren, Wenqi email: rwq.renwenqi@gmail.com organization: School of Cyber Science and Technology, Sun Yat-sen University, Guangzhou, China – sequence: 5 givenname: Bjorn surname: Stenger fullname: Stenger, Bjorn email: bjorn.stenger@gmail.com organization: Rakuten Institute of Technology, Setagaya, Tokyo, Japan – sequence: 6 givenname: Wei orcidid: 0000-0002-3865-8145 surname: Liu fullname: Liu, Wei email: wl2223@columbia.edu organization: Tencent Data Platform, Shenzhen, China – sequence: 7 givenname: Hongdong orcidid: 0000-0003-4125-1554 surname: Li fullname: Li, Hongdong email: hongdong.li@anu.edu.au organization: College of Engineering and Computer Science, The Australian National University, Canberra, Australia – sequence: 8 givenname: Ming-Hsuan orcidid: 0000-0003-4848-2304 surname: Yang fullname: Yang, Ming-Hsuan email: mhyang@ucmerced.edu organization: School of Engineering, University of California at Merced, Merced, CA, USA |
| BookMark | eNp9kEtPwzAQhC1UJNrCH0AcInFO8SN2HG5teFUq4kDhaiVm3bq0TrETJP49Lu0BceC0e5hvZ3YGqOcaBwidEzwiBBdX8_L5dT6imLIRY6RgDB-hPuFcppRi3os75iSVlPATNAhhhTHJZJb3Uf5YppN156-TcVI2m62HJbhgPyGZgNPLTeXfE9P4ZLqpFpDcQB213rrFKTo21TrA2WEO0cvd7bx8SGdP99NyPEs1LUSbCs0MYZoKYxg2WJuYydTG6EzSHMuc5jXP8kxKwQDXsuASiHljVMiay1pKNkSX-7tb33x0EFq1ajrvoqVimDNaFPGRqKJ7lfZNCB6M2nobs38pgtWuIPVTkNoVpA4FRUj-gbRtq9Y2rvWVXf-PXuxRCwC_vKjICBXsG3X8c1s |
| CODEN | ITCTEM |
| CitedBy_id | crossref_primary_10_1109_JSEN_2024_3404964 crossref_primary_10_1109_TCSVT_2023_3338689 crossref_primary_10_1109_TCI_2024_3443732 crossref_primary_10_1007_s00371_023_03229_7 crossref_primary_10_3390_rs17050834 crossref_primary_10_1016_j_neucom_2023_126996 crossref_primary_10_1109_TCSVT_2024_3424675 crossref_primary_10_1007_s11760_024_03657_5 crossref_primary_10_1109_TCSVT_2024_3486756 crossref_primary_10_1109_ACCESS_2024_3354977 crossref_primary_10_1109_TGRS_2024_3480985 |
| Cites_doi | 10.1109/TIP.2012.2192126 10.1109/CVPR52729.2023.00552 10.1109/CVPR42600.2020.00366 10.1109/CVPR.2009.5206815 10.1007/978-3-031-20071-7_29 10.1109/ICCV.2019.00897 10.1609/aaai.v34i07.6862 10.1109/CVPR52729.2023.00563 10.1109/TCSVT.2021.3093928 10.1109/ICCPhot.2012.6215221 10.1109/ICCV48922.2021.00426 10.1109/ICCV48922.2021.00460 10.1109/TCSVT.2021.3074799 10.1007/978-3-031-19797-0_24 10.1109/CVPR52729.2023.00570 10.1109/CVPR.2019.01047 10.1109/CVPR.2016.188 10.1109/CVPR42600.2020.00311 10.1007/978-3-030-58539-6_20 10.1007/978-3-319-46487-9_14 10.1109/CVPR46437.2021.01458 10.1109/CVPR.2018.00853 10.1109/ICCV.2019.00257 10.1109/ICCV.2011.6126276 10.1109/CVPR.2019.00613 10.1109/TIP.2018.2867733 10.5244/C.29.6 10.1007/s11263-022-01633-5 10.1109/ICCV.2017.435 10.1109/TCSVT.2019.2919159 10.1109/CVPRW.2019.00251 10.1109/CVPR.2017.35 10.1109/CVPR52729.2023.01344 10.1109/CVPR.2019.00184 10.1109/CVPR52729.2023.00406 10.1109/CVPRW.2019.00247 10.1007/978-3-030-58595-2_12 10.1016/j.neucom.2021.09.019 10.1109/CVPR.2019.01125 10.1109/CVPR.2017.33 10.1109/CVPR.2018.00854 10.1007/978-3-030-01237-3_45 10.1109/CVPR42600.2020.00585 10.1109/CVPR.2019.00397 10.1109/CVPR42600.2020.00281 10.1109/CVPR42600.2020.00338 10.1109/CVPR.2015.7298677 10.1109/CVPR.2018.00663 10.1109/CVPR42600.2020.00340 10.1109/TIP.2021.3101402 10.1109/ICCPHOT.2018.8368468 10.1109/TIP.2017.2753658 10.1109/CVPR.2018.00267 10.1109/CVPR46437.2021.00763 10.1109/WACV.2019.00208 10.1007/978-3-642-33786-4_3 10.1109/CVPR.2018.00862 10.1109/CVPR.2014.371 10.1109/ICCV.2019.00567 10.1109/TPAMI.2017.2753804 10.1109/CVPR.2019.00829 10.1109/TCSVT.2020.3034137 10.1109/ICCV.2017.509 10.1007/978-3-030-58607-2_7 10.1109/CVPR.2019.01048 10.1109/CVPR52688.2022.00564 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/TCSVT.2023.3319330 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library 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 |
| 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 |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2205 |
| EndPage | 3767 |
| ExternalDocumentID | 10_1109_TCSVT_2023_3319330 10264126 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 62372480 funderid: 10.13039/501100001809 – fundername: China Computer Federation (CCF)-Tencent Rhino-Bird Open Research Fund grantid: CCF-Tencent RAGR20230118 – fundername: Ford Alliance University Research Program (URP) – fundername: Australian Research Council (ARC)-Discovery grantid: DP190102261; DP220100800 funderid: 10.13039/501100000923 – fundername: Shenzhen Science and Technology Program grantid: JSGG20220831093004008 funderid: 10.13039/501100017610 – fundername: Basic and Applied Basic Research Foundation of Guangdong Province; Guangdong Basic and Applied Basic Research Foundation grantid: 2023A1515012839 funderid: 10.13039/501100021171 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT 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 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION RIG 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c296t-6c3f13c26ff30f0cf155fbffc482708727b54748863e0b8958e1fd3268b58b883 |
| IEDL.DBID | RIE |
| ISSN | 1051-8215 |
| IngestDate | Mon Jun 30 14:35:22 EDT 2025 Tue Jul 01 00:41:24 EDT 2025 Thu Apr 24 23:12:04 EDT 2025 Wed Aug 27 01:58:40 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| 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-c296t-6c3f13c26ff30f0cf155fbffc482708727b54748863e0b8958e1fd3268b58b883 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-3865-8145 0000-0003-4125-1554 0000-0002-4317-660X 0000-0003-4848-2304 0000-0001-5481-653X 0000-0002-5697-4168 0000-0002-0202-0174 |
| PQID | 3053299148 |
| PQPubID | 85433 |
| PageCount | 13 |
| ParticipantIDs | crossref_primary_10_1109_TCSVT_2023_3319330 crossref_citationtrail_10_1109_TCSVT_2023_3319330 proquest_journals_3053299148 ieee_primary_10264126 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2024-05-01 |
| PublicationDateYYYYMMDD | 2024-05-01 |
| PublicationDate_xml | – month: 05 year: 2024 text: 2024-05-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on circuits and systems for video technology |
| PublicationTitleAbbrev | TCSVT |
| PublicationYear | 2024 |
| 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 | ref13 ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref11 ref55 ref10 ref54 Nimisha (ref52) ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 ref24 ref23 ref67 ref26 ref25 ref20 ref64 ref63 ref22 ref66 ref21 ref65 ref28 ref27 ref29 ref60 ref62 ref61 |
| References_xml | – ident: ref66 doi: 10.1109/TIP.2012.2192126 – ident: ref61 doi: 10.1109/CVPR52729.2023.00552 – ident: ref56 doi: 10.1109/CVPR42600.2020.00366 – ident: ref6 doi: 10.1109/CVPR.2009.5206815 – ident: ref51 doi: 10.1007/978-3-031-20071-7_29 – ident: ref36 doi: 10.1109/ICCV.2019.00897 – ident: ref55 doi: 10.1609/aaai.v34i07.6862 – ident: ref62 doi: 10.1109/CVPR52729.2023.00563 – ident: ref58 doi: 10.1109/TCSVT.2021.3093928 – ident: ref7 doi: 10.1109/ICCPhot.2012.6215221 – ident: ref64 doi: 10.1109/ICCV48922.2021.00426 – ident: ref67 doi: 10.1109/ICCV48922.2021.00460 – ident: ref19 doi: 10.1109/TCSVT.2021.3074799 – ident: ref59 doi: 10.1007/978-3-031-19797-0_24 – ident: ref60 doi: 10.1109/CVPR52729.2023.00570 – ident: ref53 doi: 10.1109/CVPR.2019.01047 – ident: ref8 doi: 10.1109/CVPR.2016.188 – ident: ref45 doi: 10.1109/CVPR42600.2020.00311 – ident: ref57 doi: 10.1007/978-3-030-58539-6_20 – ident: ref24 doi: 10.1007/978-3-319-46487-9_14 – ident: ref40 doi: 10.1109/CVPR46437.2021.01458 – ident: ref39 doi: 10.1109/CVPR.2018.00853 – ident: ref44 doi: 10.1109/ICCV.2019.00257 – ident: ref16 doi: 10.1109/ICCV.2011.6126276 – ident: ref37 doi: 10.1109/CVPR.2019.00613 – ident: ref46 doi: 10.1109/TIP.2018.2867733 – ident: ref13 doi: 10.5244/C.29.6 – ident: ref1 doi: 10.1007/s11263-022-01633-5 – ident: ref28 doi: 10.1109/ICCV.2017.435 – ident: ref17 doi: 10.1109/TCSVT.2019.2919159 – start-page: 353 volume-title: Proc. Eur. Conf. Comput. Vis. ident: ref52 article-title: Unsupervised class-specific deblurring – ident: ref2 doi: 10.1109/CVPRW.2019.00251 – ident: ref9 doi: 10.1109/CVPR.2017.35 – ident: ref54 doi: 10.1109/CVPR52729.2023.01344 – ident: ref22 doi: 10.1109/CVPR.2019.00184 – ident: ref65 doi: 10.1109/CVPR52729.2023.00406 – ident: ref31 doi: 10.1109/CVPRW.2019.00247 – ident: ref4 doi: 10.1007/978-3-030-58595-2_12 – ident: ref48 doi: 10.1016/j.neucom.2021.09.019 – ident: ref15 doi: 10.1109/CVPR.2019.01125 – ident: ref12 doi: 10.1109/CVPR.2017.33 – ident: ref35 doi: 10.1109/CVPR.2018.00854 – ident: ref29 doi: 10.1007/978-3-030-01237-3_45 – ident: ref34 doi: 10.1109/CVPR42600.2020.00585 – ident: ref42 doi: 10.1109/CVPR.2019.00397 – ident: ref49 doi: 10.1109/CVPR42600.2020.00281 – ident: ref11 doi: 10.1109/CVPR42600.2020.00338 – ident: ref23 doi: 10.1109/CVPR.2015.7298677 – ident: ref27 doi: 10.1109/CVPR.2018.00663 – ident: ref43 doi: 10.1109/CVPR42600.2020.00340 – ident: ref47 doi: 10.1109/TIP.2021.3101402 – ident: ref50 doi: 10.1109/ICCPHOT.2018.8368468 – ident: ref26 doi: 10.1109/TIP.2017.2753658 – ident: ref38 doi: 10.1109/CVPR.2018.00267 – ident: ref63 doi: 10.1109/CVPR46437.2021.00763 – ident: ref32 doi: 10.1109/WACV.2019.00208 – ident: ref3 doi: 10.1007/978-3-642-33786-4_3 – ident: ref14 doi: 10.1109/CVPR.2018.00862 – ident: ref20 doi: 10.1109/CVPR.2014.371 – ident: ref10 doi: 10.1109/ICCV.2019.00567 – ident: ref21 doi: 10.1109/TPAMI.2017.2753804 – ident: ref30 doi: 10.1109/CVPR.2019.00829 – ident: ref18 doi: 10.1109/TCSVT.2020.3034137 – ident: ref25 doi: 10.1109/ICCV.2017.509 – ident: ref5 doi: 10.1007/978-3-030-58607-2_7 – ident: ref33 doi: 10.1109/CVPR.2019.01048 – ident: ref41 doi: 10.1109/CVPR52688.2022.00564 |
| SSID | ssj0014847 |
| Score | 2.5717814 |
| Snippet | Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 3755 |
| SubjectTerms | Benchmark testing Benchmarks Cameras Datasets Deblurring benchmark defocus deblur High definition High speed cameras Image quality Image restoration large-scale multi-cause dataset motion deblur Performance evaluation Quality assessment real-world deblur Training UHD deblur Videos |
| Title | MC-Blur: A Comprehensive Benchmark for Image Deblurring |
| URI | https://ieeexplore.ieee.org/document/10264126 https://www.proquest.com/docview/3053299148 |
| Volume | 34 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NT8IwFG-Ekx78xIii2cGb6dzWrrx5AyJBE7gIhttCSysJX2bCxb_e124QotF426Fdmvf5e-37IOQ2Egq4NBE1ECeUC1BUKhlTpk0ARscsCW3tcLcnOgP-PIyHRbG6q4XRWrvkM-3bT_eWP16qtb0qQw1H9x1GokRKKGd5sdb2yYCDmyaGeCGkgI5sUyETJPf91str37eDwn2GIsdsyvOOF3JjVX7YYudg2kektzlanlcy9dcr6avPb10b_332Y3JYQE2vkcvGCdnTi1NysNOA8IzUuy3anK2zB6_hWcuQ6Ume0O41UXon81E29RDVek9zNDse2qaZvTFcvFXIoP3Yb3VoMUqBqigRKyoUMyFTkTCGBSZQBmGEkcYo2wU0AAQxMuZ1VGbBdCAhiUGHZozQDmQMEoCdk_JiudAXxBuDYtFIGjnihkM4ggQhlcKwJ1QYGmpRJeGGtKkq-ozbcRez1MUbQZI6dqSWHWnBjiq52-55z7ts_Lm6Yum7szInbZXUNixMC038SJkdfYEgmMPlL9uuyD7-nedZjDVSXmVrfY1IYyVvnIR9AdwUy-4 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07T8MwED7xGICBN6JQIAMbckhix1zY2grUAu1CQWxR7dogUQoq7cKv5-ykqAKB2DzYsnV3vvvOvgfAcSI1CmUTZjHNmJComdIqZdzYCK1JeRa73OF2RzbvxNVD-lAmq_tcGGOMDz4zoRv6v_z-q564pzK64WS-40TOw2JKbgUW6VpfnwYCfT8xQgwxQzJl0xyZKDvtNm7vu6FrFR5yEjrugp5n7JBvrPJDG3sTc7kGnenhisiS53AyVqH--Fa38d-nX4fVEmwGtUI6NmDODDdhZaYE4RactRusPpiMzoNa4HTDyDwVIe1BneT36aU3eg4I1watF1I8AWmngXszHD5uw93lRbfRZGUzBaaTTI6Z1NzGXCfSWh7ZSFsCElZZq10d0AgJxqhUnBFRJTeRwixFE9s-gTtUKSpEvgMLw9eh2YWgj5onPWVVT1iBcQ8zAlWaHJ9Yk3NoZAXiKWlzXVYadw0vBrn3OKIs9-zIHTvykh0VOPla81bU2fhz9raj78zMgrQVqE5ZmJd38T3nrvkFwWCBe78sO4KlZrd9k9-0Otf7sEw7iSKmsQoL49HEHBDuGKtDL22fyPzPQQ |
| 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=MC-Blur%3A+A+Comprehensive+Benchmark+for+Image+Deblurring&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Zhang%2C+Kaihao&rft.au=Wang%2C+Tao&rft.au=Luo%2C+Wenhan&rft.au=Ren%2C+Wenqi&rft.date=2024-05-01&rft.issn=1051-8215&rft.eissn=1558-2205&rft.volume=34&rft.issue=5&rft.spage=3755&rft.epage=3767&rft_id=info:doi/10.1109%2FTCSVT.2023.3319330&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCSVT_2023_3319330 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon |