{"id":"https://openalex.org/W4388994449","doi":"https://doi.org/10.1145/3610543.3626177","title":"Aerial Diffusion: Text Guided Ground-to-Aerial View Synthesis from a Single Image using Diffusion Models","display_name":"Aerial Diffusion: Text Guided Ground-to-Aerial View Synthesis from a Single Image using Diffusion Models","publication_year":2023,"publication_date":"2023-11-25","ids":{"openalex":"https://openalex.org/W4388994449","doi":"https://doi.org/10.1145/3610543.3626177"},"language":"en","primary_location":{"id":"doi:10.1145/3610543.3626177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610543.3626177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610543.3626177","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Technical Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610543.3626177","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101761284","display_name":"Divya Kothandaraman","orcid":"https://orcid.org/0000-0002-6276-4968"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divya Kothandaraman","raw_affiliation_strings":["University of Maryland College Park, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-6276-4968","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, United States of America","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039076312","display_name":"Tianyi Zhou","orcid":"https://orcid.org/0000-0001-5348-0632"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhou","raw_affiliation_strings":["University of Maryland College Park, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-5348-0632","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, United States of America","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102878981","display_name":"Ming C. Lin","orcid":"https://orcid.org/0000-0003-3736-6949"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Lin","raw_affiliation_strings":["University of Maryland College Park, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3736-6949","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, United States of America","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland College Park, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7047-9801","affiliations":[{"raw_affiliation_string":"University of Maryland College Park, United States of America","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9987999796867371,"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":0.9965000152587891,"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/aerial-image","display_name":"Aerial image","score":0.8807337880134583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682234406471252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.663321852684021},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6281954050064087},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5930505394935608},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5695781707763672},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5561926364898682},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"Anisotropic diffusion","score":0.5489566326141357},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.49305960536003113},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4906124174594879},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.4532538056373596},{"id":"https://openalex.org/keywords/homography","display_name":"Homography","score":0.4450600743293762},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.43752753734588623},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17168086767196655},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.150264173746109},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08070546388626099}],"concepts":[{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.8807337880134583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682234406471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.663321852684021},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6281954050064087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5930505394935608},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5695781707763672},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5561926364898682},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.5489566326141357},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.49305960536003113},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4906124174594879},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.4532538056373596},{"id":"https://openalex.org/C28751775","wikidata":"https://www.wikidata.org/wiki/Q2112539","display_name":"Homography","level":4,"score":0.4450600743293762},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.43752753734588623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17168086767196655},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.150264173746109},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08070546388626099},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C177846678","wikidata":"https://www.wikidata.org/wiki/Q1501864","display_name":"Projective test","level":2,"score":0.0},{"id":"https://openalex.org/C75280867","wikidata":"https://www.wikidata.org/wiki/Q877775","display_name":"Projective space","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610543.3626177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610543.3626177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610543.3626177","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Technical Communications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610543.3626177","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610543.3626177","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610543.3626177","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2023 Technical Communications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388994449.pdf","grobid_xml":"https://content.openalex.org/works/W4388994449.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2125186487","https://openalex.org/W2520707372","https://openalex.org/W2886324878","https://openalex.org/W2953096069","https://openalex.org/W2963488291","https://openalex.org/W3036167779","https://openalex.org/W3155072588","https://openalex.org/W3174053790","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W4313151434","https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W1989735375","https://openalex.org/W2050662190","https://openalex.org/W1997252062","https://openalex.org/W3184611432","https://openalex.org/W2111141735"],"abstract_inverted_index":{"We":[0,30,100],"present":[1],"a":[2,12,22,61,93,110],"novel":[3],"method,":[4],"Aerial":[5,19,75,107,132],"Diffusion,":[6],"for":[7,27],"generating":[8],"aerial":[9,44,98],"views":[10,49],"from":[11],"single":[13,140],"ground-view":[14,41],"image":[15,141],"using":[16],"text":[17],"guidance.":[18],"Diffusion":[20,76,108,133],"leverages":[21],"pretrained":[23,72],"text-image":[24,55],"diffusion":[25,73],"model":[26],"prior":[28,68],"knowledge.":[29],"address":[31],"two":[32,48],"main":[33],"challenges":[34],"corresponding":[35],"to":[36,69,82],"domain":[37],"gap":[38],"between":[39],"the":[40,43,47,54,71,84,102,116,127,135],"and":[42,46,91,104,114,124,151],"view":[45],"being":[50],"far":[51],"apart":[52],"in":[53,144],"embedding":[56],"manifold.":[57],"Our":[58],"approach":[59,137],"uses":[60,77],"homography":[62],"inspired":[63],"by":[64],"inverse":[65],"perspective":[66],"mapping":[67],"finetuning":[70],"model.":[74],"an":[78,145],"alternating":[79],"sampling":[80],"strategy":[81],"compute":[83],"optimal":[85],"solution":[86],"on":[87,109],"complex":[88],"high-dimensional":[89],"manifold":[90],"generate":[92],"high-fidelity":[94],"(w.r.t.":[95],"ground":[96],"view)":[97],"image.":[99],"demonstrate":[101],"quality":[103],"versatility":[105],"of":[106,112,118,129],"plethora":[111],"images":[113],"prove":[115],"effectiveness":[117],"our":[119,130],"method":[120],"with":[121],"extensive":[122],"ablations":[123],"comparisons.":[125],"To":[126],"best":[128],"knowledge,":[131],"is":[134],"first":[136],"that":[138],"performs":[139],"ground-to-aerial":[142],"translation":[143],"unsupervised":[146],"manner.":[147],"The":[148],"full":[149],"paper":[150],"code":[152],"can":[153],"be":[154],"found":[155],"at":[156],"https://arxiv.org/abs/2303.11444.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}