{"id":"https://openalex.org/W4316660708","doi":"https://doi.org/10.1109/tim.2022.3230482","title":"Rethinking Image Deblurring via CNN-Transformer Multiscale Hybrid Architecture","display_name":"Rethinking Image Deblurring via CNN-Transformer Multiscale Hybrid Architecture","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316660708","doi":"https://doi.org/10.1109/tim.2022.3230482"},"language":"en","primary_location":{"id":"doi:10.1109/tim.2022.3230482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2022.3230482","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101658558","display_name":"Qian Zhao","orcid":"https://orcid.org/0000-0001-6190-7843"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0001-6190-7843","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101861496","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-8112-0869"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0002-8112-0869","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069672411","display_name":"Dongming Zhou","orcid":"https://orcid.org/0000-0003-0139-9415"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhou","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-0139-9415","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017808266","display_name":"Jinde Cao","orcid":"https://orcid.org/0000-0003-3133-7119"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN","KR"],"is_corresponding":false,"raw_author_name":"Jinde Cao","raw_affiliation_strings":["School of Mathematics, Southeast University, Nanjing, China","Yonsei Frontier Lab, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3133-7119","affiliations":[{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Yonsei Frontier Lab, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7654,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9218811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"72","issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deblurring","display_name":"Deblurring","score":0.9885608553886414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613592147827148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7049323320388794},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6199513077735901},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5310994386672974},{"id":"https://openalex.org/keywords/image-restoration","display_name":"Image restoration","score":0.504002034664154},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45588386058807373},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45576366782188416},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44158247113227844},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42108353972435},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41250914335250854},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3075566291809082},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2276081144809723}],"concepts":[{"id":"https://openalex.org/C2777693668","wikidata":"https://www.wikidata.org/wiki/Q25053743","display_name":"Deblurring","level":5,"score":0.9885608553886414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613592147827148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7049323320388794},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6199513077735901},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5310994386672974},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.504002034664154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45588386058807373},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45576366782188416},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44158247113227844},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42108353972435},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41250914335250854},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3075566291809082},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2276081144809723},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tim.2022.3230482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tim.2022.3230482","pdf_url":null,"source":{"id":"https://openalex.org/S10892749","display_name":"IEEE Transactions on Instrumentation and Measurement","issn_l":"0018-9456","issn":["0018-9456","1557-9662"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Instrumentation and Measurement","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G3863222636","display_name":"\u9762\u5411\u591a\u6e90\u56fe\u50cf\u878d\u5408\u8d21\u732e\u4f30\u8ba1\u7684\u591a\u6e90\u8109\u51b2\u4fe1\u606f\u4ea4\u6362\u7f16\u7801\u4e0e\u5206\u6570\u9636\u53d8\u5206\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61966037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6968482730","display_name":"\u590d\u6742\u75be\u75c5\u7684\u57fa\u56e0\u8c03\u63a7\u7f51\u7edc\u5efa\u6a21\u6280\u672f\u7814\u7a76\u4e0e\u5e94\u7528","funder_award_id":"62066047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W233979554","https://openalex.org/W1522301498","https://openalex.org/W1580389772","https://openalex.org/W1916935112","https://openalex.org/W2046119925","https://openalex.org/W2124500511","https://openalex.org/W2167307343","https://openalex.org/W2194775991","https://openalex.org/W2560023338","https://openalex.org/W2560533888","https://openalex.org/W2564023417","https://openalex.org/W2573798160","https://openalex.org/W2607041014","https://openalex.org/W2759428153","https://openalex.org/W2765507148","https://openalex.org/W2788790154","https://openalex.org/W2806224701","https://openalex.org/W2899663614","https://openalex.org/W2920770442","https://openalex.org/W2961218591","https://openalex.org/W2962785568","https://openalex.org/W2962803115","https://openalex.org/W2963263347","https://openalex.org/W2963312584","https://openalex.org/W2963814095","https://openalex.org/W2964030969","https://openalex.org/W2965217508","https://openalex.org/W2966284335","https://openalex.org/W2975950300","https://openalex.org/W2982795046","https://openalex.org/W2988641380","https://openalex.org/W2998249728","https://openalex.org/W3013529009","https://openalex.org/W3017136408","https://openalex.org/W3018757597","https://openalex.org/W3034789174","https://openalex.org/W3035484352","https://openalex.org/W3040557872","https://openalex.org/W3085824656","https://openalex.org/W3097463671","https://openalex.org/W3097762837","https://openalex.org/W3105070560","https://openalex.org/W3106135392","https://openalex.org/W3107405705","https://openalex.org/W3120680448","https://openalex.org/W3124818450","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3155350616","https://openalex.org/W3170697543","https://openalex.org/W3171125843","https://openalex.org/W3174756006","https://openalex.org/W3193296307","https://openalex.org/W3200683480","https://openalex.org/W3202040256","https://openalex.org/W3203848400","https://openalex.org/W3207516177","https://openalex.org/W3210068417","https://openalex.org/W3212022416","https://openalex.org/W3213236098","https://openalex.org/W4213019189","https://openalex.org/W4220863475","https://openalex.org/W4220974521","https://openalex.org/W4225672218","https://openalex.org/W4226043703","https://openalex.org/W4282575541","https://openalex.org/W4285105199","https://openalex.org/W4285105754","https://openalex.org/W4288700147","https://openalex.org/W4312812783","https://openalex.org/W4312938066","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6755977528","https://openalex.org/W6777046832","https://openalex.org/W6789816031"],"related_works":["https://openalex.org/W2066613488","https://openalex.org/W2031788393","https://openalex.org/W791927757","https://openalex.org/W2182590612","https://openalex.org/W3153582293","https://openalex.org/W2905397092","https://openalex.org/W2269775642","https://openalex.org/W3080537281","https://openalex.org/W2289746762","https://openalex.org/W2139384960"],"abstract_inverted_index":{"Image":[0],"deblurring":[1,31,41,178,194,231],"is":[2,180],"a":[3,89,94,143],"representative":[4],"low-level":[5],"vision":[6,248],"task":[7],"that":[8,87,98,154],"aims":[9],"to":[10,65,67,123,135,147,192,200,238],"estimate":[11],"latent":[12],"sharp":[13],"images":[14,45],"from":[15,34],"blurred":[16,44],"images.":[17],"Recently,":[18],"convolutional":[19,62],"neural":[20],"network":[21,146],"(CNN)-based":[22],"methods":[23,32,42],"have":[24],"dominated":[25],"image":[26,236],"deblurring.":[27],"However,":[28],"traditional":[29],"CNN-based":[30],"suffer":[33],"two":[35],"essential":[36],"issues:":[37],"first,":[38],"existing":[39],"multiscale":[40,85],"process":[43],"at":[46],"different":[47],"scales":[48],"through":[49],"sub-networks":[50,112,153],"with":[51,119],"the":[52,57,61,68,79,84,110,125,129,149,169,197,216,228,240],"same":[53],"composition,":[54],"which":[55,131,166],"limits":[56],"model":[58,179],"performance.":[59],"Second,":[60],"layers":[63],"fail":[64],"adapt":[66],"input":[69,156],"content":[70,157],"and":[71,92,101,172,187,204,212,235],"cannot":[72],"effectively":[73],"capture":[74],"long-range":[75],"dependencies.":[76],"To":[77],"alleviate":[78,148],"above":[80],"issues,":[81],"we":[82,141,160,222],"rethink":[83],"architecture":[86,97],"follows":[88],"coarse-to-fine":[90],"strategy":[91],"propose":[93,142],"novel":[95],"hybrid":[96],"combines":[99],"CNN":[100,152],"transformer":[102,164],"(CTMS).":[103],"CTMS":[104,114,243],"has":[105],"three":[106],"distinct":[107],"features.":[108],"First,":[109],"finer-scale":[111],"in":[113],"are":[115,209],"designed":[116],"as":[117],"architectures":[118],"larger":[120],"receptive":[121],"fields":[122],"obtain":[124],"pixel":[126],"values":[127,208],"around":[128],"blur,":[130],"can":[132],"be":[133],"used":[134],"efficiently":[136],"handle":[137],"large-area":[138],"blur.":[139],"Then,":[140],"feature":[144],"modulation":[145],"disadvantages":[150],"of":[151,242],"lack":[155],"adaptation.":[158],"Finally,":[159],"design":[161],"an":[162],"efficient":[163],"block,":[165],"significantly":[167],"reduces":[168],"computational":[170],"burden":[171],"requires":[173],"no":[174],"pre-training.":[175],"Our":[176],"proposed":[177,229],"extensively":[181],"evaluated":[182],"on":[183,215,227],"several":[184],"benchmark":[185],"datasets,":[186],"achieves":[188],"superior":[189],"performance":[190],"compared":[191],"state-of-the-art":[193],"methods.":[195],"Especially,":[196],"peak":[198],"signal":[199],"noise":[201],"ratio":[202],"(PSNR)":[203],"structural":[205],"similarity":[206],"(SSIM)":[207],"32.73":[210],"dB":[211],"0.959,":[213],"respectively,":[214],"popular":[217],"dataset":[218],"GoPro.":[219],"In":[220],"addition,":[221],"conduct":[223],"joint":[224],"evaluation":[225],"experiments":[226],"method":[230],"performance,":[232],"object":[233],"detection,":[234],"segmentation":[237],"demonstrate":[239],"effectiveness":[241],"for":[244],"subsequent":[245],"high-level":[246],"computer":[247],"tasks.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}