{"id":"https://openalex.org/W4417174896","doi":"https://doi.org/10.1109/iccv51701.2025.01704","title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","display_name":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417174896","doi":"https://doi.org/10.1109/iccv51701.2025.01704"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.00992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuanrui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanrui Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070924148","display_name":"Cong Han","orcid":"https://orcid.org/0000-0002-0418-6143"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440730","display_name":"Yafei Li","orcid":"https://orcid.org/0000-0003-2587-820X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Li","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725735","display_name":"Zhipeng Jin","orcid":"https://orcid.org/0009-0003-0863-2539"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Jin","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102833206","display_name":"Xiawei Li","orcid":"https://orcid.org/0000-0002-2709-7020"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiawei Li","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102598017","display_name":"Sinan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"SiNan Du","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749804","display_name":"Tao Wen","orcid":"https://orcid.org/0000-0002-8253-9338"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Tao","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102858978","display_name":"Shuanglong Li","orcid":"https://orcid.org/0000-0003-4802-9884"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuanglong Li","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109125095","display_name":"Chun Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383255","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0001-5733-6910"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Lin","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]}],"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":"18335","last_page":"18344"},"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":0.6865000128746033,"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":0.6865000128746033,"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":0.1428000032901764,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/glyph","display_name":"Glyph (data visualization)","score":0.8446999788284302},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6276999711990356},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5593000054359436},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.538100004196167},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.39010000228881836},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38089999556541443},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.3772999942302704},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34850001335144043},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.8446999788284302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004999756813049},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738000273704529},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35409998893737793},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25290000438690186},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.00992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00992","pdf_url":"https://arxiv.org/pdf/2507.00992","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.00992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.00992","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":"pmh:oai:arXiv.org:2507.00992","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00992","pdf_url":"https://arxiv.org/pdf/2507.00992","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4213465990","display_name":null,"funder_award_id":"2022YFB4701400/4701402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,172],"has":[2],"greatly":[3],"advanced":[4],"content":[5,125],"creation,":[6],"yet":[7],"accurately":[8],"rendering":[9,199],"visual":[10,70],"text":[11,71,101,176,198],"remains":[12],"a":[13,64,94,106,116,188],"key":[14],"challenge":[15],"due":[16],"to":[17,39,119],"blurred":[18],"glyphs,":[19],"semantic":[20],"drift,":[21],"and":[22,44,55,79,104,115,126,144,162,168,200,208],"limited":[23],"style":[24],"control.":[25],"Existing":[26],"methods":[27,140,186],"often":[28],"rely":[29],"on":[30,133],"pre-rendered":[31],"glyph":[32,76,113,163],"images":[33],"as":[34,83],"conditions,":[35],"but":[36],"these":[37,60],"struggle":[38],"retain":[40],"original":[41],"font":[42],"styles":[43],"color":[45],"cues,":[46],"necessitating":[47],"complex":[48,166,201],"multi-branch":[49],"designs":[50],"that":[51,67,181],"increase":[52],"model":[53,98,109,183],"overhead":[54],"reduce":[56],"flexibility.":[57],"To":[58,147],"address":[59],"issues,":[61],"we":[62,152],"propose":[63],"segmentation-guided":[65],"framework":[66],"uses":[68],"pixel-level":[69],"masks":[72],"--":[73,82],"rich":[74],"in":[75,123,141,165,174,191],"shape,":[77],"color,":[78],"spatial":[80],"detail":[81],"unified":[84],"conditional":[85],"inputs.":[86],"Our":[87,128],"method":[88],"introduces":[89],"two":[90,155],"core":[91],"components:":[92],"(1)":[93],"fine-tuned":[95],"bilingual":[96],"segmentation":[97],"for":[99,159,170],"precise":[100],"mask":[102],"extraction,":[103],"(2)":[105],"streamlined":[107],"diffusion":[108],"augmented":[110],"with":[111],"adaptive":[112],"conditioning":[114],"region-specific":[117],"loss":[118],"preserve":[120],"textual":[121],"fidelity":[122],"both":[124,142,192],"style.":[127],"approach":[129],"achieves":[130],"state-of-the-art":[131],"performance":[132],"the":[134],"AnyText":[135],"benchmark,":[136],"significantly":[137],"surpassing":[138],"prior":[139],"Chinese":[143],"English":[145],"settings.":[146],"enable":[148],"more":[149],"rigorous":[150],"evaluation,":[151],"also":[153],"introduce":[154],"new":[156],"benchmarks:":[157],"GlyphMM-benchmark":[158],"testing":[160],"layout":[161,202],"consistency":[164],"typesetting,":[167],"MiniText-benchmark":[169],"assessing":[171],"quality":[173],"small-scale":[175],"regions.":[177],"Experimental":[178],"results":[179],"show":[180],"our":[182],"outperforms":[184],"existing":[185],"by":[187],"large":[189],"margin":[190],"scenarios,":[193],"particularly":[194],"excelling":[195],"at":[196],"small":[197],"preservation,":[203],"validating":[204],"its":[205],"strong":[206],"generalization":[207],"deployment":[209],"readiness.":[210]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}