{"id":"https://openalex.org/W7162022582","doi":"https://doi.org/10.48550/arxiv.2605.21090","title":"TextSculptor: Training and Benchmarking Scene Text Editing","display_name":"TextSculptor: Training and Benchmarking Scene Text Editing","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162022582","doi":"https://doi.org/10.48550/arxiv.2605.21090"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136689389","display_name":"Yiheng Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049196219","display_name":"Siyu Jiao","orcid":"https://orcid.org/0000-0002-0795-8401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136707930","display_name":"Xiaohan Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136665358","display_name":"Zhou, Wei, 1968 Jan. 17-","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136641917","display_name":"Qi She","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"She, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136689048","display_name":"Fei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136723414","display_name":"Heyun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Heyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514726","display_name":"Zhengwei Wang","orcid":"https://orcid.org/0000-0001-7706-553X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076959824","display_name":"Jinghuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinghuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083232013","display_name":"Moran Li","orcid":"https://orcid.org/0000-0002-8149-1117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Moran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136698700","display_name":"Yingchen Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136638514","display_name":"Zijian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136724958","display_name":"Yao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136642102","display_name":"Yunchao Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Yunchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136704371","display_name":"Yujie Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yujie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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":0.5295000076293945,"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":0.5295000076293945,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.18619999289512634,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05310000106692314,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5794000029563904},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.578499972820282},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3662000000476837},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34470000863075256},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.3312999904155731},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.3273000121116638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169999718666077},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5794000029563904},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4228000044822693},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3312999904155731},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2988504831","wikidata":"https://www.wikidata.org/wiki/Q1192366","display_name":"Text entry","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21090","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4195065498352051}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"and":[8,37,57,80,103,124,135,157,175,184,197,206],"diffusion-based":[9],"generative":[10],"models":[11,27,42],"have":[12],"substantially":[13],"improved":[14],"prompt-driven":[15],"image":[16,97],"editing.":[17,66,85,159],"However,":[18],"scene":[19,83],"text":[20,65,84,101,127,148,151,153,155,171,180,194],"editing":[21,128,149,195],"remains":[22],"challenging,":[23],"as":[24],"it":[25],"requires":[26],"to":[28,50,64,201],"precisely":[29],"modify":[30],"textual":[31],"content":[32],"while":[33],"preserving":[34],"visual":[35,173],"realism":[36],"non-target":[38],"regions.":[39],"Current":[40],"open-source":[41,193],"still":[43],"lag":[44],"behind":[45],"proprietary":[46,202],"systems,":[47],"largely":[48],"due":[49],"the":[51,58,199],"scarcity":[52],"of":[53,60,82],"high-quality":[54],"training":[55,117],"data":[56,78,91,205],"lack":[59],"standardized":[61],"benchmarks":[62],"tailored":[63,167],"To":[67,160],"address":[68],"these":[69],"challenges,":[70],"we":[71,109,164],"present":[72],"TextSculptor,":[73],"a":[74,112,143,166],"comprehensive":[75],"framework":[76],"for":[77],"construction":[79,92],"evaluation":[81],"We":[86,139],"first":[87],"develop":[88],"an":[89],"automated":[90],"pipeline":[93],"that":[94,169,190],"combines":[95],"text-aware":[96],"synthesis":[98],"with":[99,130],"programmatic":[100],"rendering":[102],"compositing.":[104],"Based":[105],"on":[106],"this":[107],"pipeline,":[108],"build":[110],"TextSculpt-Data,":[111],"large-scale":[113],"dataset":[114],"containing":[115],"3.2M":[116],"samples,":[118],"including":[119],"1.2M":[120],"OCR-verified":[121],"text-to-image":[122],"samples":[123,129],"2M":[125],"paired":[126],"naturally":[131],"aligned":[132],"source-target":[133],"images":[134],"strong":[136],"background":[137,176],"consistency.":[138],"further":[140],"introduce":[141],"TextSculpt-Bench,":[142],"benchmark":[144,207],"covering":[145],"four":[146],"fundamental":[147],"tasks:":[150],"addition,":[152],"replacement,":[154],"removal,":[156],"hybrid":[158],"support":[161],"reliable":[162],"evaluation,":[163],"design":[165],"protocol":[168],"measures":[170],"accuracy,":[172],"quality,":[174],"preservation":[177],"through":[178],"OCR-based":[179],"alignment,":[181],"multimodal":[182],"judgment,":[183],"background-region":[185],"similarity.":[186],"Extensive":[187],"experiments":[188],"show":[189],"TextSculptor":[191],"improves":[192],"performance":[196],"narrows":[198],"gap":[200],"models.":[203],"The":[204],"are":[208],"available":[209],"at":[210],"https://github.com/linyiheng123/TextSculptor.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}