{"id":"https://openalex.org/W4414715920","doi":"https://doi.org/10.1016/j.visinf.2025.100283","title":"Knowledge and multi-detail enhanced GAN for human-driven text-to-image synthesis","display_name":"Knowledge and multi-detail enhanced GAN for human-driven text-to-image synthesis","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414715920","doi":"https://doi.org/10.1016/j.visinf.2025.100283"},"language":"en","primary_location":{"id":"doi:10.1016/j.visinf.2025.100283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100283","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.visinf.2025.100283","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054900679","display_name":"Ning Xu","orcid":"https://orcid.org/0000-0002-7526-4356"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ning Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114230301","display_name":"Zhewen Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhewen Shen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019994406","display_name":"Hongshuo Tian","orcid":"https://orcid.org/0000-0001-7635-0961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongshuo Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063699066","display_name":"Bolun Zheng","orcid":"https://orcid.org/0000-0001-8788-1725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bolun Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054311881","display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0003-1204-0512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837799","display_name":"Jinbo Cao","orcid":"https://orcid.org/0009-0002-2044-3549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinbo Cao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062258244","display_name":"Rongbao Kang","orcid":"https://orcid.org/0000-0001-8487-8520"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongbao Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5054900679"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27657367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"1","first_page":"100283","last_page":"100283"},"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":0.9958000183105469,"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":0.9958000183105469,"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":0.9927999973297119,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.991599977016449,"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/gallium-nitride","display_name":"Gallium nitride","score":0.4984999895095825},{"id":"https://openalex.org/keywords/wide-bandgap-semiconductor","display_name":"Wide-bandgap semiconductor","score":0.28610000014305115},{"id":"https://openalex.org/keywords/semiconductor-materials","display_name":"Semiconductor materials","score":0.1987999975681305},{"id":"https://openalex.org/keywords/crystal","display_name":"Crystal (programming language)","score":0.17880000174045563}],"concepts":[{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.6340000033378601},{"id":"https://openalex.org/C2778871202","wikidata":"https://www.wikidata.org/wiki/Q411713","display_name":"Gallium nitride","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C49040817","wikidata":"https://www.wikidata.org/wiki/Q193091","display_name":"Optoelectronics","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.4399999976158142},{"id":"https://openalex.org/C189278905","wikidata":"https://www.wikidata.org/wiki/Q2157708","display_name":"Wide-bandgap semiconductor","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.22540000081062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.21250000596046448},{"id":"https://openalex.org/C61696701","wikidata":"https://www.wikidata.org/wiki/Q770766","display_name":"Engineering physics","level":1,"score":0.2004999965429306},{"id":"https://openalex.org/C2989315489","wikidata":"https://www.wikidata.org/wiki/Q2659774","display_name":"Semiconductor materials","level":3,"score":0.1987999975681305},{"id":"https://openalex.org/C2781285689","wikidata":"https://www.wikidata.org/wiki/Q21921428","display_name":"Crystal (programming language)","level":2,"score":0.17880000174045563}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.visinf.2025.100283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100283","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.visinf.2025.100283","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100283","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1861492603","https://openalex.org/W1885185971","https://openalex.org/W2194775991","https://openalex.org/W2341528187","https://openalex.org/W2970562079","https://openalex.org/W2996605677","https://openalex.org/W3035574324","https://openalex.org/W3096831136","https://openalex.org/W3101998545","https://openalex.org/W3203312420","https://openalex.org/W4213227099","https://openalex.org/W4224035735","https://openalex.org/W4224081694","https://openalex.org/W4289785095","https://openalex.org/W4296935086","https://openalex.org/W4301206121","https://openalex.org/W4310443798","https://openalex.org/W4327842770","https://openalex.org/W4376645463","https://openalex.org/W4385848774","https://openalex.org/W4386977133","https://openalex.org/W4388570742","https://openalex.org/W4390136668","https://openalex.org/W4402753775","https://openalex.org/W4402774219","https://openalex.org/W4402782221"],"related_works":[],"abstract_inverted_index":{"Human-driven":[0],"text-to-image":[1,126],"synthesis":[2],"aims":[3,44],"to":[4,12,45,75,134,147,156,163,172,189,197,233],"create":[5],"controllable":[6],"images,":[7],"which":[8,182,208,238],"not":[9],"only":[10,276],"adhere":[11],"the":[13,21,33,42,50,53,95,103,106,115,122,136,154,164,174,179,184,199,204,230,235,241,254,279],"semantic":[14],"of":[15,24,40,85,92,124,187,244,249,256,278],"given":[16,25,29,165],"text":[17],"but":[18],"also":[19],"incorporate":[20],"visual":[22],"characteristics":[23],"human.":[26],"For":[27],"example,":[28],"\u201ca":[30],"man":[31],"on":[32,52,288],"beach\u201d":[34],"(text)":[35],"along":[36],"with":[37,100,259],"a":[38,77],"photo":[39],"human,":[41,212],"model":[43],"generate":[46],"an":[47],"image":[48,97,185],"depicting":[49],"human":[51,86,93,139,149,175,191,245],"beach.":[54],"Although":[55],"current":[56],"diffusion-based":[57,273],"methods":[58],"have":[59],"shown":[60],"promise":[61],"in":[62,94,102,284],"this":[63],"task,":[64],"they":[65],"face":[66],"two":[67,286],"major":[68],"limitations:":[69],"(1)":[70],"The":[71,90],"generated":[72,96],"images":[73,159],"appear":[74],"be":[76],"bit":[78],"stiff":[79],"and":[80,87,117,140,142,214,221,247,262,281],"unnatural,":[81],"almost":[82],"like":[83],"collages":[84],"backgrounds;":[88],"(2)":[89],"details":[91,246],"are":[98,161],"inconsistent":[99],"those":[101],"input,":[104],"losing":[105],"original":[107],"identity.":[108],"To":[109],"address":[110],"these":[111],"issues,":[112],"we":[113,152,177,202,228],"present":[114,178,203],"Knowledge":[116,205],"Multi-Detail":[118,180],"Enhanced":[119],"GAN":[120],"for":[121],"task":[123],"human-driven":[125],"synthesis.":[127],"It":[128,266],"employs":[129],"external":[130,158],"knowledge":[131,215],"as":[132,168],"references":[133],"improve":[135],"harmony":[137],"between":[138],"backgrounds,":[141],"uses":[143,183,275],"CLIP\u2019s":[144],"multi-layer":[145],"features":[146],"intensify":[148],"details.":[150],"First,":[151],"search":[153],"database":[155],"retrieve":[157],"that":[160],"similar":[162],"text,":[166,213],"serving":[167],"our":[169,257],"knowledge.":[170,226],"Second,":[171],"preserve":[173],"details,":[176],"Enhancer,":[181,207],"encoder":[186],"CLIP":[188],"extract":[190],"representation":[192],"at":[193],"multiple":[194],"levels.":[195],"Third,":[196],"enhance":[198],"human-background":[200],"naturalness,":[201],"Attention":[206],"can":[209,239],"seamlessly":[210],"blend":[211],"by":[216],"attentively":[217],"retain":[218],"useful":[219],"information":[220],"filter":[222],"out":[223],"noise":[224],"from":[225],"Finally,":[227],"introduce":[229],"dual":[231],"discriminators":[232],"guide":[234],"entire":[236],"network,":[237],"facilitate":[240],"accurate":[242],"capture":[243],"generation":[248],"images.":[250],"Extensive":[251],"experiments":[252],"demonstrate":[253],"superiority":[255],"method":[258],"its":[260],"efficiency":[261],"lower":[263],"computational":[264],"demands.":[265],"is":[267],"about":[268],"300":[269],"times":[270],"faster":[271],"than":[272],"models,":[274],"5%":[277],"parameters,":[280],"completes":[282],"training":[283],"just":[285],"days":[287],"three":[289],"V100":[290],"GPUs.":[291]},"counts_by_year":[],"updated_date":"2026-03-17T06:59:57.516163","created_date":"2025-10-10T00:00:00"}