{"id":"https://openalex.org/W4409263230","doi":"https://doi.org/10.1109/wacv61041.2025.00523","title":"Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance","display_name":"Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4409263230","doi":"https://doi.org/10.1109/wacv61041.2025.00523"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61041.2025.00523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5092094033","display_name":"Ahmad Arrabi","orcid":null},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Arrabi","raw_affiliation_strings":["University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science","institution_ids":["https://openalex.org/I111236770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431066","display_name":"Xiaohan Zhang","orcid":"https://orcid.org/0000-0001-6344-9604"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohan Zhang","raw_affiliation_strings":["University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science","institution_ids":["https://openalex.org/I111236770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082613558","display_name":"Waqas Sultani","orcid":"https://orcid.org/0000-0002-9322-0728"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I4210159412","display_name":"Intelligent Machines (Sweden)","ror":"https://ror.org/05nzk9q32","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210159412"]}],"countries":["PK","SE"],"is_corresponding":false,"raw_author_name":"Waqas Sultani","raw_affiliation_strings":["Information Technology University,Intelligent Machines Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology University,Intelligent Machines Lab","institution_ids":["https://openalex.org/I4210159412","https://openalex.org/I1323252656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317030","display_name":"Chen Chen","orcid":"https://orcid.org/0009-0001-2214-3323"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["University of Central Florida,Center for Research in Computer Vision"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida,Center for Research in Computer Vision","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001816279","display_name":"Safwan Wshah","orcid":"https://orcid.org/0000-0001-5051-7719"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Safwan Wshah","raw_affiliation_strings":["University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Vermont,Vermont Artificial Intelligence Lab,Department of Computer Science","institution_ids":["https://openalex.org/I111236770"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5446,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.96674861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5356","last_page":"5366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9939000010490417,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9939000010490417,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9746000170707703,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5700721740722656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5585487484931946},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5250151753425598},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4964292645454407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47859975695610046},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.42547863721847534},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4030199646949768},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17525696754455566},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15852677822113037}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5700721740722656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5585487484931946},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5250151753425598},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4964292645454407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47859975695610046},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.42547863721847534},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4030199646949768},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17525696754455566},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15852677822113037},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61041.2025.00523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61041.2025.00523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3481635175","display_name":null,"funder_award_id":"2218063","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2007582554","https://openalex.org/W2024339093","https://openalex.org/W2133665775","https://openalex.org/W2162909892","https://openalex.org/W2164271227","https://openalex.org/W2194775991","https://openalex.org/W2199890863","https://openalex.org/W2563705555","https://openalex.org/W2626107033","https://openalex.org/W2734349601","https://openalex.org/W2793872863","https://openalex.org/W2890179025","https://openalex.org/W2953096069","https://openalex.org/W2962785568","https://openalex.org/W2963021791","https://openalex.org/W2963474852","https://openalex.org/W3016821823","https://openalex.org/W3034680896","https://openalex.org/W3092933908","https://openalex.org/W3096934659","https://openalex.org/W3120991189","https://openalex.org/W3135662255","https://openalex.org/W3174800995","https://openalex.org/W3179267034","https://openalex.org/W3181256602","https://openalex.org/W3203158837","https://openalex.org/W3205150709","https://openalex.org/W4220773950","https://openalex.org/W4285161910","https://openalex.org/W4312311094","https://openalex.org/W4312443924","https://openalex.org/W4312597490","https://openalex.org/W4312641958","https://openalex.org/W4312933868","https://openalex.org/W4367359628","https://openalex.org/W4382467090","https://openalex.org/W4386057708","https://openalex.org/W4386072002","https://openalex.org/W4386076520","https://openalex.org/W4388796689","https://openalex.org/W4390873054","https://openalex.org/W4393148714","https://openalex.org/W4402917057","https://openalex.org/W6745136726","https://openalex.org/W6765779288","https://openalex.org/W6766729115","https://openalex.org/W6788990321","https://openalex.org/W6794013123","https://openalex.org/W6809885388","https://openalex.org/W6840425996","https://openalex.org/W6845281891","https://openalex.org/W6855878887","https://openalex.org/W6856551304","https://openalex.org/W6857529801","https://openalex.org/W6860041859"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Aerial":[0],"imagery":[1],"analysis":[2],"is":[3,15,29,47],"critical":[4],"for":[5,185],"many":[6],"research":[7],"fields.":[8],"However,":[9,45],"obtaining":[10],"frequent":[11],"high-quality":[12],"aerial":[13,38,87,123,158,173],"images":[14,39,88,174],"not":[16,56],"always":[17],"accessible":[18],"due":[19],"to":[20,30,36,108,192],"its":[21,52],"high":[22],"effort":[23],"and":[24,64,131,161,188,202],"cost":[25],"requirements.":[26],"One":[27],"solution":[28],"use":[31],"the":[32,59,101,110,115,122,126,135,195],"Ground-to-Aerial":[33,77],"(G2A)":[34,78],"technique":[35],"synthesize":[37],"from":[40,89,114,125],"easily":[41],"collectible":[42],"ground":[43,90,116,136],"images.":[44,91],"G2A":[46],"rarely":[48],"studied,":[49],"because":[50],"of":[51,66,94,134,197],"challenges,":[53],"including":[54],"but":[55],"limited":[57],"to,":[58],"drastic":[60],"view":[61],"changes,":[62],"occlusion,":[63],"range":[65],"visibil-ity.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,142],"present":[72,143,180],"a":[73,144],"novel":[74],"Geometric":[75],"Preserving":[76],"image":[79,124],"synthesis":[80],"(GPG2A)":[81],"model":[82],"that":[83,168],"can":[84],"generate":[85],"realistic":[86],"GPG2A":[92,169],"consists":[93],"two":[95,181],"stages.":[96],"The":[97,118,200],"first":[98],"stage":[99,120],"predicts":[100],"Bird's":[102],"Eye":[103],"View":[104],"(BEV)":[105],"segmentation":[106],"(referred":[107],"as":[109],"BEV":[111,128],"layout":[112,129],"map)":[113],"image.":[117,137],"second":[119],"synthesizes":[121,170],"predicted":[127],"map":[130],"text":[132,162],"descriptions":[133],"To":[138],"train":[139],"our":[140,198],"model,":[141],"new":[145],"multimodal":[146],"cross-view":[147,186],"dataset,":[148],"namely":[149],"VIGORv2,":[150],"built":[151],"upon":[152],"VIGOR":[153],"[64]":[154],"with":[155],"newly":[156],"collected":[157],"images,":[159],"maps,":[160],"descriptions.":[163],"Our":[164],"extensive":[165],"experiments":[166],"illustrate":[167],"better":[171],"geometry-preserved":[172],"than":[175],"existing":[176],"models.":[177],"We":[178],"also":[179],"applications,":[182],"data":[183],"augmentation":[184],"geo-localization":[187],"sketch-based":[189],"region":[190],"search,":[191],"further":[193],"verify":[194],"effectiveness":[196],"GPG2A.":[199],"code":[201],"dataset":[203],"are":[204],"available":[205],"at":[206],"https://github.com/AhmadArrabi/GPG2A.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}