{"id":"https://openalex.org/W7141352833","doi":"https://doi.org/10.1111/cgf.70342","title":"TextFlux: An OCR\u2010Free DiT Model for High\u2010Fidelity Multilingual Scene Text Synthesis","display_name":"TextFlux: An OCR\u2010Free DiT Model for High\u2010Fidelity Multilingual Scene Text Synthesis","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7141352833","doi":"https://doi.org/10.1111/cgf.70342"},"language":"en","primary_location":{"id":"doi:10.1111/cgf.70342","is_oa":false,"landing_page_url":"https://doi.org/10.1111/cgf.70342","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","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/A5100992291","display_name":"Yu Xie","orcid":"https://orcid.org/0009-0007-1695-9370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Xie","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0007-1695-9370","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130735155","display_name":"Jielei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jielei Zhang","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0005-9449-7189","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146812743","display_name":"Pengyu Chen","orcid":"https://orcid.org/0009-0008-0587-3771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Chen","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0008-0587-3771","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130739427","display_name":"Weihang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihang Wang","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0008-4504-4441","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017145972","display_name":"Longwen Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longwen Gao","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0000-0621-2950","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130803096","display_name":"Peiyi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiyi Li","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0007-7351-1986","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130795218","display_name":"Qian Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Qiao","raw_affiliation_strings":["Bilibili Inc.  China"],"raw_orcid":"https://orcid.org/0009-0005-6154-1411","affiliations":[{"raw_affiliation_string":"Bilibili Inc.  China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114425298","display_name":"Zhouhui Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhouhui Lian","raw_affiliation_strings":["Wangxuan Institute of ComputerTechnology Peking University  China"],"raw_orcid":"https://orcid.org/0000-0002-2683-7170","affiliations":[{"raw_affiliation_string":"Wangxuan Institute of ComputerTechnology Peking University  China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5114425298"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":3710,"currency":"USD","value_usd":3710},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31587064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6929000020027161,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6929000020027161,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09830000251531601,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.023000000044703484,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.839900016784668},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5968000292778015},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46219998598098755},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3833000063896179},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.902400016784668},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.839900016784668},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5293999910354614},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4772999882698059},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1111/cgf.70342","is_oa":false,"landing_page_url":"https://doi.org/10.1111/cgf.70342","pdf_url":null,"source":{"id":"https://openalex.org/S67831204","display_name":"Computer Graphics Forum","issn_l":"0167-7055","issn":["0167-7055","1467-8659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Graphics Forum","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2965463054","https://openalex.org/W3204777666","https://openalex.org/W3212516020","https://openalex.org/W4386072096","https://openalex.org/W4386075667","https://openalex.org/W4386076215","https://openalex.org/W4393147980","https://openalex.org/W4393148714","https://openalex.org/W4402727190","https://openalex.org/W4402727368","https://openalex.org/W4403792358","https://openalex.org/W4413145131","https://openalex.org/W4413156045","https://openalex.org/W4413156664","https://openalex.org/W7133230457"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Diffusion\u2010based":[1],"scene":[2,51,74],"text":[3,75,151],"synthesis":[4,157],"has":[5],"progressed":[6],"rapidly,":[7],"yet":[8],"existing":[9],"methods":[10,163,179],"commonly":[11],"rely":[12],"on":[13],"additional":[14],"visual":[15,103],"conditioning":[16],"modules":[17,37],"and":[18,38,48,117,172,183],"require":[19],"large\u2010scale":[20],"annotated":[21],"data":[22,143],"to":[23,101,165],"support":[24],"multilingual":[25,73,108,115],"generation.":[26,152],"In":[27],"this":[28,63],"work,":[29],"we":[30,65],"revisit":[31],"the":[32,92,141],"necessity":[33],"of":[34,79,140],"complex":[35],"auxiliary":[36],"further":[39],"explore":[40],"an":[41],"approach":[42],"that":[43,71,97,175],"simultaneously":[44],"ensures":[45],"glyph":[46],"accuracy":[47],"achieves":[49,118],"high\u2010fidelity":[50],"integration,":[52],"by":[53,145],"leveraging":[54],"diffusion":[55],"models'":[56],"inherent":[57],"capabilities":[58],"for":[59,94],"contextual":[60],"reasoning.":[61],"To":[62],"end,":[64],"introduce":[66],"TextFlux,":[67],"a":[68],"DiT\u2010based":[69],"framework":[70],"enables":[72],"synthesis.":[76],"The":[77],"advantages":[78],"TextFlux":[80,90,110,134,153,176],"can":[81],"be":[82],"summarized":[83],"as":[84],"follows:":[85],"(1)":[86],"OCR\u2010free":[87],"model":[88],"architecture.":[89],"eliminates":[91],"need":[93],"OCR":[95],"encoders":[96],"are":[98],"specifically":[99],"used":[100],"extract":[102],"text\u2010related":[104],"features.":[105],"(2)":[106],"Strong":[107],"scalability.":[109],"is":[111,135,188],"effective":[112],"in":[113,121,180],"low\u2010resource":[114],"settings,":[116],"strong":[119],"performance":[120],"newly":[122],"added":[123],"languages":[124],"with":[125,137,158],"fewer":[126],"than":[127],"1,000":[128],"samples.":[129],"(3)":[130],"Streamlined":[131],"training":[132,142],"setup.":[133],"trained":[136],"only":[138],"1%":[139],"required":[144],"competing":[146],"methods.":[147],"(4)":[148],"Controllable":[149],"multi\u2010line":[150,156],"offers":[154],"flexible":[155],"precise":[159],"line\u2010level":[160],"control,":[161],"outperforming":[162],"restricted":[164],"single\u2010line":[166],"or":[167],"rigid":[168],"layouts.":[169],"Extensive":[170],"experiments":[171],"visualizations":[173],"demonstrate":[174],"outperforms":[177],"previous":[178],"both":[181],"qualitative":[182],"quantitative":[184],"evaluations.":[185],"Our":[186],"code":[187],"available":[189],"at":[190],"https://github.com/yyyyyxie/textflux":[191],".":[192]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-03-28T00:00:00"}