{"id":"https://openalex.org/W4413145264","doi":"https://doi.org/10.1109/cvpr52734.2025.01243","title":"From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing","display_name":"From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145264","doi":"https://doi.org/10.1109/cvpr52734.2025.01243"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5101761718","display_name":"Jingxuan Wei","orcid":"https://orcid.org/0000-0001-8520-6347"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Wei","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100877979","display_name":"Cheng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Tan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017281141","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-7539-8728"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103637441","display_name":"Gaowei Wu","orcid":"https://orcid.org/0000-0003-2104-972X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaowei Wu","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406609","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0001-6806-2468"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060075172","display_name":"Zhangyang Gao","orcid":"https://orcid.org/0000-0003-1026-6083"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangyang Gao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101227392","display_name":"Linzhuang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhuang Sun","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043026583","display_name":"Bihui Yu","orcid":"https://orcid.org/0000-0001-8614-7350"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bihui Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090901690","display_name":"Ruifeng Guo","orcid":"https://orcid.org/0000-0003-3345-0502"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifeng Guo","raw_affiliation_strings":["Chinese Academy of Sciences,Shenyang Institute of Computing Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenyang Institute of Computing Technology","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.8466,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96873133,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13315","last_page":"13325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.7302453517913818},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6769240498542786},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.66068434715271},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4013855457305908},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34412890672683716},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3394497036933899},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12120917439460754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302453517913818},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6769240498542786},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.66068434715271},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4013855457305908},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34412890672683716},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3394497036933899},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12120917439460754},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318567","display_name":"Westlake University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2134604260","https://openalex.org/W2963935794","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W4252326246","https://openalex.org/W4385562549","https://openalex.org/W4385801730","https://openalex.org/W4387506531","https://openalex.org/W4391468387","https://openalex.org/W4399379055","https://openalex.org/W4401024413","https://openalex.org/W4402670103","https://openalex.org/W4402671772","https://openalex.org/W4402704640","https://openalex.org/W4402976435","https://openalex.org/W4403601051","https://openalex.org/W4404199100","https://openalex.org/W4404783012","https://openalex.org/W4404783273","https://openalex.org/W4411113317"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"We":[0],"introduce":[1,54],"the":[2,26,95,137],"task":[3,140],"of":[4,99,122],"text-to-diagram":[5,138],"generation,":[6],"which":[7,105],"focuses":[8],"on":[9],"creating":[10],"structured":[11],"visual":[12],"representations":[13],"directly":[14],"from":[15],"textual":[16],"descriptions.":[17],"Existing":[18],"approaches":[19],"in":[20,39,120,152],"text-to-image":[21],"and":[22,29,70,89,97,126,150],"text-to-code":[23],"generation":[24,96,139],"lack":[25],"logical":[27],"organization":[28],"flexibility":[30],"needed":[31],"to":[32,47,92,147],"produce":[33],"accurate,":[34],"editable":[35],"diagrams,":[36,69],"often":[37],"resulting":[38],"outputs":[40],"that":[41,113],"are":[42],"either":[43],"unstructured":[44],"or":[45],"difficult":[46],"modify.":[48],"To":[49],"address":[50],"this":[51,153],"gap,":[52],"we":[53,74],"DiagramGenBenchmark,":[55],"a":[56,133,144],"comprehensive":[57],"evaluation":[58],"framework":[59,79],"encompassing":[60],"eight":[61],"distinct":[62],"diagram":[63],"categories,":[64],"including":[65],"flowcharts,":[66],"model":[67],"architecture":[68],"mind":[71],"maps.":[72],"Additionally,":[73],"present":[75],"DiagramAgent,":[76],"an":[77],"innovative":[78],"with":[80,109],"four":[81],"core":[82],"modules\u2014Plan":[83],"Agent,":[84,86,88],"Code":[85],"Check":[87],"Diagram-to-Code":[90],"Agent\u2014designed":[91],"facilitate":[93],"both":[94],"refinement":[98],"complex":[100],"diagrams.":[101],"Our":[102],"extensive":[103],"experiments,":[104],"combine":[106],"objective":[107],"metrics":[108],"human":[110],"evaluations,":[111],"demonstrate":[112],"DiagramAgent":[114],"significantly":[115],"outperforms":[116],"existing":[117],"baseline":[118],"models":[119],"terms":[121],"accuracy,":[123],"structural":[124],"coherence,":[125],"modifiability.":[127],"This":[128],"work":[129],"not":[130],"only":[131],"establishes":[132],"foundational":[134],"benchmark":[135],"for":[136],"but":[141],"also":[142],"introduces":[143],"powerful":[145],"toolset":[146],"advance":[148],"research":[149],"applications":[151],"emerging":[154],"area.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
