{"id":"https://openalex.org/W7138279667","doi":"https://doi.org/10.1609/aaai.v40i15.38283","title":"Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description","display_name":"Any2RSI: Controllable Remote Sensing Text-to-Image Generation via Any Control and Enriched Description","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138279667","doi":"https://doi.org/10.1609/aaai.v40i15.38283"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i15.38283","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38283","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i15.38283","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129742590","display_name":"Xu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745743","display_name":"Jianzhong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Huang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129751065","display_name":"Lefei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefei Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":6.9212,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9465812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"40","issue":"15","first_page":"12852","last_page":"12860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6814000010490417,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6814000010490417,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04820000007748604,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.04659999907016754,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.6527000069618225},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5392000079154968},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5195000171661377},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.49399998784065247},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3393000066280365},{"id":"https://openalex.org/keywords/spatial-coherence","display_name":"Spatial coherence","score":0.32659998536109924},{"id":"https://openalex.org/keywords/remote-sensing-application","display_name":"Remote sensing application","score":0.32429999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311999797821045},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C183365957","wikidata":"https://www.wikidata.org/wiki/Q17140402","display_name":"Remote sensing application","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32330000400543213},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C557691694","wikidata":"https://www.wikidata.org/wiki/Q185091","display_name":"Remote control","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i15.38283","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38283","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38283","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38283","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38283","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,11,153],"controllable":[3,82],"text-to-image":[4],"(T2I)":[5],"generation":[6],"have":[7],"achieved":[8],"impressive":[9],"results":[10],"natural":[12],"images,":[13],"but":[14],"remote":[15],"sensing":[16],"(RS)":[17],"T2I":[18,84],"remains":[19],"challenging":[20],"due":[21],"to":[22,32,44],"the":[23,171],"unique":[24],"nature":[25],"of":[26,176],"geospatial":[27],"data.":[28],"Existing":[29],"methods":[30],"struggle":[31],"integrate":[33],"diverse":[34,148],"spatial":[35,40,98,102],"controls":[36],"and":[37,68,167,173],"model":[38],"complex":[39],"relationships,":[41],"often":[42],"failing":[43],"maintain":[45],"semantic":[46],"consistency":[47],"with":[48,65,124,140],"typically":[49],"vague":[50],"or":[51,108],"incomplete":[52],"textual":[53],"descriptions.":[54],"Moreover,":[55],"limited":[56],"by":[57],"small-scale,":[58],"low-quality":[59],"datasets,":[60,169],"these":[61,73],"models":[62],"produce":[63],"outputs":[64],"inconsistent":[66],"layouts":[67],"unrealistic":[69],"content.":[70],"To":[71,104],"address":[72],"issues,":[74],"we":[75,112,133],"propose":[76],"Any2RSI,":[77],"a":[78,88,114,136],"flexible":[79],"framework":[80],"for":[81,106,127],"RS":[83,144,178],"generation.":[85,131],"It":[86],"features":[87],"Cross-Modal":[89],"Multi-Control":[90],"Adapter":[91],"that":[92,120,159],"extracts":[93],"modality-agnostic":[94],"embeddings":[95],"from":[96],"heterogeneous":[97],"inputs,":[99],"enabling":[100],"precise":[101],"guidance.":[103],"compensate":[105],"sparse":[107],"ambiguous":[109],"text":[110],"prompts,":[111],"introduce":[113],"VLM-Empowered":[115],"Enriched":[116],"Description":[117],"Generation":[118],"module":[119],"enhances":[121],"input":[122],"descriptions":[123],"cross-modal":[125],"semantics":[126],"more":[128],"coherent":[129],"image":[130],"Furthermore,":[132],"present":[134],"RST2I-110K,":[135],"new":[137,168],"large-scale":[138],"dataset":[139],"over":[141],"115,000":[142],"high-quality":[143],"image-text":[145],"pairs":[146],"across":[147],"scenes,":[149],"alleviating":[150],"data":[151],"scarcity":[152],"this":[154],"domain.":[155],"Extensive":[156],"experiments":[157],"show":[158],"Any2RSI":[160],"achieves":[161],"state-of-the-art":[162],"performance":[163],"on":[164],"both":[165],"existing":[166],"improving":[170],"realism":[172],"structural":[174],"accuracy":[175],"generated":[177],"imagery.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}