{"id":"https://openalex.org/W4415539777","doi":"https://doi.org/10.1145/3746027.3755613","title":"RealText: Realistic Text Image Generation based on Glyph and Scene Aware Inpainting","display_name":"RealText: Realistic Text Image Generation based on Glyph and Scene Aware Inpainting","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539777","doi":"https://doi.org/10.1145/3746027.3755613"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050213654","display_name":"Z.S. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihou Liu","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0529-0228","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632765","display_name":"Dongming Zhang","orcid":"https://orcid.org/0000-0002-1237-7177"},"institutions":[{"id":"https://openalex.org/I4210121144","display_name":"China Machine Press","ror":"https://ror.org/02t1dzr71","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210121144"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongming Zhang","raw_affiliation_strings":["State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1237-7177","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China","institution_ids":["https://openalex.org/I4210121144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032383728","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-1290-0738"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1290-0738","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112086045","display_name":"Jun Li","orcid":"https://orcid.org/0009-0006-3176-8030"},"institutions":[{"id":"https://openalex.org/I4210121144","display_name":"China Machine Press","ror":"https://ror.org/02t1dzr71","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210121144"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3176-8030","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Communication Content Cognition, People's Daily Online, Beijing, China","institution_ids":["https://openalex.org/I4210121144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100419834","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0003-0066-3448"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0066-3448","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10379","last_page":"10387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9930999875068665,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9930999875068665,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.992900013923645,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9927999973297119,"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/glyph","display_name":"Glyph (data visualization)","score":0.6158999800682068},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5652999877929688},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.47589999437332153},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.44690001010894775},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.436599999666214},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.42890000343322754},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.4239000082015991},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4138000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097000122070312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7421000003814697},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6506999731063843},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.6158999800682068},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.44690001010894775},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.4239000082015991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C84392682","wikidata":"https://www.wikidata.org/wiki/Q1952404","display_name":"Multilinear map","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C3019635856","wikidata":"https://www.wikidata.org/wiki/Q1619726","display_name":"Background image","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C61265191","wikidata":"https://www.wikidata.org/wiki/Q767770","display_name":"Scale-invariant feature transform","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3096831136","https://openalex.org/W4390873054"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,59,178,189],"models":[2],"can":[3,169],"create":[4],"diverse,":[5],"high-quality":[6],"images,":[7],"but":[8],"they":[9],"frequently":[10],"encounter":[11],"challenges":[12],"in":[13,43,51,200],"accurately":[14],"rendering":[15],"text":[16,39,49,57,68,89,101,119,135,166,176],"within":[17],"those":[18],"images":[19,40,50,58,98,202],"due":[20],"to":[21,78,117,133,160],"the":[22,80,96,110,139,152,194],"insufficient":[23],"representation":[24],"of":[25,82,99,141,154,197],"desired":[26],"text.":[27,205],"In":[28,109],"this":[29],"study,":[30],"we":[31,75,94,113,168],"introduce":[32],"RealText,":[33],"a":[34,183],"method":[35,199],"for":[36],"generating":[37,148,201],"scene":[38,48,56,115,126,163,175],"that":[41],"excels":[42],"producing":[44],"precise":[45,172],"and":[46,64,70,122,130,156,165],"realistic":[47],"any":[52],"language.":[53],"We":[54,180],"disentangle":[55],"into":[60],"three":[61],"stages:":[62],"background":[63,84,155],"glyph":[65,97,157,161],"image":[66,72,150,177],"generation,":[67],"deformation,":[69,136],"whole":[71],"generation.":[73],"Initially,":[74],"utilize":[76],"prompts":[77],"guide":[79],"creation":[81],"well-organized":[83],"images.":[85,143],"By":[86],"identifying":[87],"optimal":[88],"placements":[90],"on":[91],"these":[92],"backgrounds,":[93],"render":[95],"target":[100],"using":[102,128],"user-specified":[103],"font,":[104],"effectively":[105],"eliminating":[106],"incorrect":[107],"characters.":[108],"next":[111],"stage,":[112],"propose":[114],"sensing":[116],"perceive":[118],"carrier":[120],"surfaces":[121],"viewpoints":[123],"through":[124],"3D":[125],"reconstruction":[127],"depth":[129],"normal":[131],"map":[132],"apply":[134],"thereby":[137],"enhancing":[138],"realism":[140],"generated":[142],"The":[144,206],"final":[145],"stage":[146],"involves":[147],"complete":[149],"with":[151,203],"aid":[153],"guidance.":[158],"Thanks":[159],"disentangling,":[162],"sensing,":[164],"inpainting,":[167],"exert":[170],"more":[171],"control":[173],"over":[174],"process.":[179],"have":[181],"developed":[182],"unified":[184],"framework":[185],"which":[186],"supports":[187],"major":[188],"models.":[190],"Extensive":[191],"experiments":[192],"illustrate":[193],"exceptional":[195],"performance":[196],"our":[198],"multilingual":[204],"codes":[207],"will":[208],"soon":[209],"be":[210],"available":[211],"at":[212],"https://github.com/cccvl/RealText.":[213]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}