{"id":"https://openalex.org/W7166880339","doi":"https://doi.org/10.1016/j.eswa.2026.133491","title":"High-fidelity text refinement for ControlNet-guided latent diffusion in document inpainting","display_name":"High-fidelity text refinement for ControlNet-guided latent diffusion in document inpainting","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7166880339","doi":"https://doi.org/10.1016/j.eswa.2026.133491"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.133491","doi":"https://doi.org/10.1016/j.eswa.2026.133491","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.133491","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-c","doyens","fnege-3","jufo-2","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.eswa.2026.133491","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097605614","display_name":"Qinglin Mao","orcid":"https://orcid.org/0000-0002-0938-0690","observed_orcids":["https://orcid.org/0000-0002-0938-0690"]},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Mao","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China"],"raw_orcid":"https://orcid.org/0000-0002-0938-0690","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021734426","display_name":"Shengzhe Xu","orcid":"https://orcid.org/0009-0009-4030-2824","observed_orcids":["https://orcid.org/0009-0009-4030-2824","https://orcid.org/0009-0002-2191-7187"]},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengzhe Xu","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China"],"raw_orcid":"https://orcid.org/0009-0002-2191-7187","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003644414","display_name":"Songliang Chen","orcid":"https://orcid.org/0009-0001-1225-8151","observed_orcids":["https://orcid.org/0009-0001-1225-8151"]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songliang Chen","raw_affiliation_strings":["Key Laboratory of Groundwater Resources and Environment, Ministry of Education, Jilin University, Changchun, 130021, China"],"raw_orcid":"https://orcid.org/0009-0001-1225-8151","affiliations":[{"raw_affiliation_string":"Key Laboratory of Groundwater Resources and Environment, Ministry of Education, Jilin University, Changchun, 130021, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139806060","display_name":"Hang Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhou","raw_affiliation_strings":["Nottingham University Business School China, University of Nottingham, Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nottingham University Business School China, University of Nottingham, Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028555014","display_name":"Pushpendu Kar","orcid":"https://orcid.org/0000-0002-0896-0650","observed_orcids":["https://orcid.org/0000-0002-0896-0650","https://orcid.org/0000-0003-4410-1172"]},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pushpendu Kar","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China"],"raw_orcid":"https://orcid.org/0000-0002-0896-0650","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035490114","display_name":"Anthony Graham Bellotti","orcid":"https://orcid.org/0000-0001-6317-5877","observed_orcids":["https://orcid.org/0000-0001-6317-5877"]},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anthony Graham Bellotti","raw_affiliation_strings":["School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China"],"raw_orcid":"https://orcid.org/0000-0001-6317-5877","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, 315100, China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035490114"],"corresponding_institution_ids":["https://openalex.org/I13591777"],"apc_list":{"value":3500,"currency":"USD","value_usd":3500},"apc_paid":{"value":3500,"currency":"USD","value_usd":3500},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47667618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"332","issue":null,"first_page":"133491","last_page":"133491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6797000169754028,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6797000169754028,"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":0.2761000096797943,"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":0.027699999511241913,"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/controlnet","display_name":"ControlNet","score":0.9039999842643738},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9100000262260437},{"id":"https://openalex.org/keywords/ocr-error-correction","display_name":"OCR error correction","score":0.5669999718666077},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8169999718666077},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9490000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355000019073486},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.708299994468689},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5755000114440918},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5637999773025513},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2529999911785126},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.eswa.2026.133491","doi":"https://doi.org/10.1016/j.eswa.2026.133491","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.133491","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-c","doyens","fnege-3","jufo-2","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.5886006","doi":"https://doi.org/10.2139/ssrn.5886006","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.5886006","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1016/j.eswa.2026.133491","doi":"https://doi.org/10.1016/j.eswa.2026.133491","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.133491","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-c","doyens","fnege-3","jufo-2","ki-jl-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G374571540","display_name":null,"funder_award_id":"2021B-008-C","funder_id":"https://openalex.org/F4320322213","funder_display_name":"Ningbo Municipal People's Government"},{"id":"https://openalex.org/G8667151263","display_name":null,"funder_award_id":"22DF_AGB","funder_id":"https://openalex.org/F4320337088","funder_display_name":"University of Nottingham Ningbo China"}],"funders":[{"id":"https://openalex.org/F4320322213","display_name":"Ningbo Municipal People's Government","ror":"https://ror.org/025ras206"},{"id":"https://openalex.org/F4320337088","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2798365772","https://openalex.org/W2997154779","https://openalex.org/W4285146136","https://openalex.org/W4286238648","https://openalex.org/W4304013646","https://openalex.org/W4387967972","https://openalex.org/W4393148079","https://openalex.org/W4403780713","https://openalex.org/W4404436774","https://openalex.org/W4405847559","https://openalex.org/W4406762297","https://openalex.org/W4406857481","https://openalex.org/W7123342962","https://openalex.org/W7152701423"],"related_works":[],"abstract_inverted_index":{"Blind":[0],"document":[1,9,67,193],"image":[2,102,175],"inpainting":[3],"(DII)":[4],"aims":[5],"to":[6,73],"restore":[7],"degraded":[8],"scans":[10],"without":[11],"prior":[12],"knowledge":[13],"of":[14,119,134],"noise":[15],"locations,":[16],"yet":[17],"existing":[18],"methods":[19,171],"either":[20],"produce":[21],"over-smoothed":[22],"text":[23,71,82],"or":[24],"introduce":[25,114],"pseudo-characters.":[26],"We":[27],"propose":[28,140],"a":[29,37,52,92,146,187],"novel":[30,147],"high-fidelity,":[31],"text-guided":[32],"restoration":[33,154],"framework":[34],"based":[35],"on":[36,161],"ControlNet-guided":[38],"Latent":[39],"Diffusion":[40],"Model":[41,56,61],"(CGLDM).":[42],"First,":[43],"we":[44,113,139],"extract":[45],"and":[46,58,69,99,130,177],"refine":[47],"noisy":[48],"OCR":[49,178],"outputs":[50],"using":[51,141],"two-stage":[53],"Vision":[54],"Language":[55,60],"(VLM)":[57],"Large":[59],"(LLM)":[62],"pipeline,":[63],"leveraging":[64],"both":[65,173],"global":[66],"context":[68],"local":[70],"cues":[72],"deliver":[74],"near":[75],"ground-truth":[76,136],"textual":[77,151],"fidelity.":[78],"Next,":[79],"these":[80],"refined":[81],"features,":[83],"together":[84],"with":[85],"an":[86,115],"initial":[87],"visually":[88],"restored":[89],"image,":[90],"condition":[91],"latent":[93],"diffusion":[94,120],"process":[95],"that":[96,123,166],"progressively":[97],"denoises":[98],"reconstructs":[100],"clean":[101],"latents.":[103],"To":[104],"suppress":[105],"patch-wise":[106],"background":[107],"inconsistencies":[108],"inherent":[109],"in":[110,156,172],"high-resolution":[111],"processing,":[112],"explicit":[116],"feature-alignment":[117],"loss":[118],"model":[121],"training":[122],"enforces":[124],"agreement":[125],"between":[126],"the":[127,131,135,162],"predicted":[128],"features":[129,133],"VAE-encoded":[132],"image.":[137],"Finally,":[138],"PNG":[142],"file":[143],"size":[144],"as":[145],"non-reference":[148],"metric\u2014under":[149],"preserved":[150],"legibility\u2014to":[152],"quantify":[153],"quality":[155,176],"ill-posed":[157],"settings.":[158],"Extensive":[159],"experiments":[160],"FUNSD-ZH":[163],"dataset":[164],"demonstrate":[165],"our":[167],"approach":[168],"outperforms":[169],"state-of-the-art":[170],"perceptual":[174],"legibility,":[179],"while":[180],"achieving":[181],"superior":[182],"compression":[183],"efficiency,":[184],"thereby":[185],"offering":[186],"practical,":[188],"trustworthy":[189],"solution":[190],"for":[191],"real-world":[192],"recovery.":[194]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-07-02T00:00:00"}