{"id":"https://openalex.org/W4410584054","doi":"https://doi.org/10.23919/date64628.2025.10993256","title":"AeroDiffusion: Complex Aerial Image Synthesis with Keypoint-Aware Text Descriptions and Feature-Augmented Diffusion Models","display_name":"AeroDiffusion: Complex Aerial Image Synthesis with Keypoint-Aware Text Descriptions and Feature-Augmented Diffusion Models","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410584054","doi":"https://doi.org/10.23919/date64628.2025.10993256"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10993256","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10993256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5115513937","display_name":"Douglas Townsell","orcid":null},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas J. Townsell","raw_affiliation_strings":["Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059911353","display_name":"Mimi Xie","orcid":"https://orcid.org/0000-0003-1973-2909"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mimi Xie","raw_affiliation_strings":["University of Texas at San Antonio,Department of Computer Science,San Antonio,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio,Department of Computer Science,San Antonio,TX,USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398270","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-4606-8532"},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045929043","display_name":"Fathi Amsaad","orcid":"https://orcid.org/0000-0002-1641-5046"},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fathi Amsaad","raw_affiliation_strings":["Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117630490","display_name":"Varshitha Reddy Thanam","orcid":null},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varshitha Reddy Thanam","raw_affiliation_strings":["Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100444341","display_name":"Wen Zhang","orcid":"https://orcid.org/0000-0001-6087-5202"},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Zhang","raw_affiliation_strings":["Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wright State University,Department of Computer Science and Engineering,Dayton,OH,USA","institution_ids":["https://openalex.org/I19648265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2384,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77056574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9912999868392944,"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":0.9912999868392944,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9911999702453613,"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":0.9771999716758728,"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/feature","display_name":"Feature (linguistics)","score":0.709943413734436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.705894947052002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6617427468299866},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5492827296257019},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5100094079971313},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.46314379572868347},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4571594297885895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4508058428764343},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3569510877132416},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06044363975524902},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0567454993724823}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.709943413734436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705894947052002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617427468299866},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5492827296257019},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5100094079971313},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.46314379572868347},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4571594297885895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4508058428764343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3569510877132416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06044363975524902},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0567454993724823},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10993256","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10993256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W3002706778","https://openalex.org/W3035574168","https://openalex.org/W3040983344","https://openalex.org/W3096831136","https://openalex.org/W3205612999","https://openalex.org/W3210997132","https://openalex.org/W3211904225","https://openalex.org/W4226437079","https://openalex.org/W4283711834","https://openalex.org/W4293243615","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4387166575","https://openalex.org/W4389610328","https://openalex.org/W4390264354","https://openalex.org/W4390872325","https://openalex.org/W4393148753","https://openalex.org/W4393241094","https://openalex.org/W4394593186","https://openalex.org/W4399487330","https://openalex.org/W4399952535","https://openalex.org/W4402727378","https://openalex.org/W4402754016","https://openalex.org/W6679045638","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6809646742","https://openalex.org/W6811013733","https://openalex.org/W6838639034","https://openalex.org/W6838865847"],"related_works":["https://openalex.org/W1989735375","https://openalex.org/W2034727732","https://openalex.org/W2127305659","https://openalex.org/W2050609384","https://openalex.org/W2054964223","https://openalex.org/W1992574978","https://openalex.org/W2901309398","https://openalex.org/W2064075093","https://openalex.org/W3147584709","https://openalex.org/W2977677679"],"abstract_inverted_index":{"Aerial":[0],"imagery":[1],"provides":[2],"crucial":[3],"insights":[4],"for":[5,110,120,155],"various":[6],"fields,":[7],"including":[8,161],"remote":[9],"monitoring,":[10],"environmental":[11],"assessment,":[12],"and":[13,29,53,83,115,134,177,204],"autonomous":[14],"navigation.":[15],"However,":[16],"the":[17,34,71,77,84,148,162,179],"availability":[18],"of":[19,36,73,79,86,142,164,181,188],"aerial":[20,67,144,158],"image":[21,45,122,159,175],"datasets":[22],"is":[23,147],"limited":[24],"due":[25,69],"to":[26,51,70,100,130,138,150],"privacy":[27],"concerns":[28],"imbalanced":[30],"data":[31],"distribution,":[32],"impeding":[33],"development":[35],"robust":[37],"deep":[38,152],"learning":[39],"models.":[40],"Recent":[41],"advancements":[42],"in":[43,64],"text-guided":[44,157],"synthesis":[46],"offer":[47],"a":[48,96,116,171],"promising":[49],"approach":[50,125],"enrich":[52],"diversify":[54],"these":[55,102],"datasets.":[56],"Despite":[57],"progress,":[58],"existing":[59],"generative":[60,153],"models":[61,108,154,196],"face":[62],"challenges":[63,103],"synthesizing":[65],"realistic":[66,121],"images":[68,165],"lack":[72],"paired":[74,173],"text-aerial":[75,174],"datasets,":[76],"complexity":[78],"densely":[80],"packed":[81],"objects,":[82],"limitations":[85],"modeling":[87],"object":[88],"relationships.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"introduce":[94],"AeroDiffusion,":[95],"novel":[97,167],"framework":[98],"designed":[99],"overcome":[101],"by":[104],"leveraging":[105],"large":[106],"language":[107],"(LLMs)":[109],"keypoint-aware":[111],"text":[112],"description":[113],"generation":[114],"feature-augmented":[117],"diffusion":[118],"process":[119],"synthesis.":[123],"Our":[124],"integrates":[126],"region-level":[127],"feature":[128,136],"extraction":[129],"preserve":[131],"small":[132],"objects":[133],"multimodal":[135],"alignment":[137],"improve":[139],"textual":[140],"descriptions":[141],"complex":[143],"scenes.":[145],"AeroDiffusion":[146],"first":[149],"extend":[151],"high-resolution,":[156],"generation,":[160],"creation":[163],"from":[166],"viewpoints.":[168],"We":[169],"contribute":[170],"new":[172],"dataset":[176],"demonstrate":[178],"effectiveness":[180],"our":[182],"model,":[183],"achieving":[184],"an":[185],"FID":[186],"score":[187],"78.15":[189],"across":[190],"five":[191],"benchmarks,":[192],"significantly":[193],"outperforming":[194],"state-of-the-art":[195],"such":[197],"as":[198],"DDPM":[199],"(217.95),":[200],"Stable":[201],"Diffusion":[202],"(119.13),":[203],"ARLDM":[205],"(111.59).":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}