{"id":"https://openalex.org/W7118216567","doi":"https://doi.org/10.1109/tcsvt.2026.3650924","title":"Collaborative Refinement Guidance for High-Fidelity Defect Image Synthesis","display_name":"Collaborative Refinement Guidance for High-Fidelity Defect Image Synthesis","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118216567","doi":"https://doi.org/10.1109/tcsvt.2026.3650924"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3650924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3650924","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5116749037","display_name":"Weihang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihang Luo","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0008-1342-0158","affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080807489","display_name":"Xingen Gao","orcid":"https://orcid.org/0009-0000-7385-5825"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingen Gao","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0000-7385-5825","affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121936573","display_name":"Zhijie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Zhang","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianxiongwen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiongwen Huang","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121938240","display_name":"Hongyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Zhang","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-1532-8303","affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096749833","display_name":"Juqiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juqiang Lin","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121064584","display_name":"Hua Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Shi","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0001-8812-5737","affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121789761","display_name":"Huanqiang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqiang Zeng","raw_affiliation_strings":["School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-2802-7745","affiliations":[{"raw_affiliation_string":"School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75867142"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01732095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6414","last_page":"6427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.8148000240325928,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.8148000240325928,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.10450000315904617,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01860000006854534,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5932999849319458},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5669999718666077},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5478000044822693},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46309998631477356},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4277999997138977},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42149999737739563},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3961000144481659},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3937999904155731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5857999920845032},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5669999718666077},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42149999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3650924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3650924","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5134967565536499,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3404856863","display_name":null,"funder_award_id":"62372392","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7319665869","display_name":null,"funder_award_id":"3502Z20234033","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"Visual":[1],"Inspection":[2],"is":[3,17,30,53,115,217],"a":[4,56,111,118,147,155,181],"cornerstone":[5],"of":[6,12,25,149],"modern":[7],"manufacturing,":[8],"yet":[9],"the":[10,21,68,106,131,142,173],"development":[11],"robust":[13],"deep":[14],"learning":[15],"models":[16],"frequently":[18],"impeded":[19],"by":[20,108],"scarcity":[22,200],"and":[23,90,195],"imbalance":[24],"training":[26,136],"data.":[27],"This":[28],"challenge":[29],"particularly":[31],"acute":[32],"for":[33,60,208],"industrial":[34,202],"defects,":[35],"which":[36,74,114],"often":[37,186],"manifest":[38],"as":[39,55,192],"subtle":[40],"anomalies":[41],"intrinsically":[42],"linked":[43],"to":[44,86,97,121,151,154,172,198],"complex,":[45],"structured":[46],"backgrounds.":[47],"To":[48],"address":[49],"this":[50],"challenge,":[51],"CRG-DefectDiffuser":[52,191],"proposed":[54],"collaborative":[57],"generative":[58],"framework":[59,162],"high-fidelity":[61],"defect":[62,95,100,143],"synthesis.":[63],"At":[64],"its":[65],"core":[66],"lies":[67],"Collaborative":[69],"Refinement":[70],"Guidance":[71],"(CRG)":[72],"mechanism,":[73],"orchestrates":[75],"two":[76],"specialized":[77],"diffusion":[78],"models:":[79],"one":[80],"trained":[81,92],"on":[82,93],"abundant":[83],"defect-free":[84],"images":[85],"master":[87],"background":[88,133],"context,":[89],"another":[91],"scarce":[94],"patches":[96],"encode":[98],"fine-grained":[99],"semantics.":[101],"The":[102,161,214],"CRG":[103],"mechanism":[104],"steers":[105],"synthesis":[107],"dynamically":[109],"generating":[110],"guidance":[112],"map,":[113],"refined":[116],"through":[117],"four-stage":[119],"process":[120],"ensure":[122],"that":[123],"morphologically":[124],"accurate":[125],"defects":[126],"are":[127],"seamlessly":[128],"integrated":[129],"into":[130],"appropriate":[132],"context.":[134],"Augmenting":[135],"data":[137,175,199],"with":[138,167,205],"our":[139,179],"method":[140],"boosts":[141],"detection":[144],"mAP@50-95":[145],"from":[146],"baseline":[148],"0.496":[150],"0.557,":[152],"corresponding":[153],"12.3":[156],"percentage":[157],"point":[158,182],"relative":[159],"improvement.":[160],"also":[163],"demonstrates":[164],"superior":[165],"scalability,":[166],"performance":[168],"gains":[169],"continuing":[170],"up":[171],"three-fold":[174],"augmentation":[176],"evaluated":[177],"in":[178,201],"experiments,":[180],"where":[183],"competing":[184],"methods":[185],"falter.":[187],"These":[188],"results":[189],"establish":[190],"an":[193],"effective":[194],"practical":[196],"solution":[197],"visual":[203],"inspection,":[204],"strong":[206],"potential":[207],"generalization":[209],"across":[210],"diverse":[211],"manufacturing":[212],"scenarios.":[213],"source":[215],"code":[216],"publicly":[218],"available":[219],"at":[220],"https://github.com/weihang-luo/":[221],"CRG-DefectDiffuser.":[222]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-01-05T00:00:00"}