{"id":"https://openalex.org/W4402263177","doi":"https://doi.org/10.1109/igarss53475.2024.10641523","title":"Diffusion-Geo: A Two-Stage Controllable Text-To-Image Generative Model for Remote Sensing Scenarios","display_name":"Diffusion-Geo: A Two-Stage Controllable Text-To-Image Generative Model for Remote Sensing Scenarios","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4402263177","doi":"https://doi.org/10.1109/igarss53475.2024.10641523"},"language":"en","primary_location":{"id":"doi:10.1109/igarss53475.2024.10641523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","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/A5102999194","display_name":"Miaoxin Cai","orcid":"https://orcid.org/0009-0007-2584-5949"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Miaoxin Cai","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092401779","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0003-7332-126X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Beijing Institute of Technology,Advanced Research Institute of Multidisciplinary Sciences,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Advanced Research Institute of Multidisciplinary Sciences,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688517","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-1769-9829"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023179941","display_name":"Yin Zhuang","orcid":"https://orcid.org/0000-0002-0443-1081"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhuang","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327676","display_name":"He Chen","orcid":"https://orcid.org/0000-0002-5441-6752"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Chen","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334649","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0003-1453-1091"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chen","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334051","display_name":"Can Li","orcid":"https://orcid.org/0000-0002-5529-0688"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Li","raw_affiliation_strings":["Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102999194"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.5005,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83758792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7003","last_page":"7006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9764000177383423,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9764000177383423,"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":0.9559999704360962,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9506999850273132,"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/computer-science","display_name":"Computer science","score":0.6737616658210754},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6114028096199036},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6048676371574402},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5981180667877197},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.574414849281311},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5160760283470154},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4455321431159973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41036832332611084},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3959025740623474},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.20738160610198975},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0999671220779419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737616658210754},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6114028096199036},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6048676371574402},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5981180667877197},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.574414849281311},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5160760283470154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4455321431159973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41036832332611084},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3959025740623474},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.20738160610198975},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0999671220779419},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/igarss53475.2024.10641523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/igarss53475.2024.10641523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3130754787","https://openalex.org/W3180045188","https://openalex.org/W4365800965","https://openalex.org/W4387717533","https://openalex.org/W4388685775","https://openalex.org/W4390873054","https://openalex.org/W6790978476","https://openalex.org/W6858380932"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Image":[0],"generation":[1,19,82],"is":[2,73,86,116],"a":[3,65,120],"crucial":[4],"task":[5,59,137],"to":[6,118],"facilitate":[7],"intelligent":[8],"interpretation":[9],"in":[10,31,43,169],"remote":[11,32],"sensing":[12,33],"domain.":[13],"Expanding":[14],"dataset":[15,83,115,154,159],"size":[16],"through":[17,88],"image":[18,123,170],"can":[20,55],"enhance":[21],"model":[22,70,134],"performance":[23],"of":[24,53,91,163],"downtown":[25],"task.":[26],"However,":[27],"current":[28],"generative":[29,69,124],"models":[30,95,168],"are":[34],"mostly":[35],"unconditional":[36],"or":[37],"guided":[38],"by":[39],"simple":[40],"text,":[41],"resulting":[42],"generated":[44],"images":[45],"lacking":[46],"spatial":[47,109],"and":[48,97,110,145,155],"semantic":[49,111],"constraints.":[50],"This":[51],"lack":[52],"control":[54],"negatively":[56],"optimize":[57],"downstream":[58],"models.":[60],"To":[61],"tackle":[62],"these":[63],"challenges,":[64],"two-stage":[66],"controllable":[67,122],"text-image":[68],"called":[71,84],"Diffusion-Geo":[72,164],"presented.":[74],"In":[75],"the":[76,132,151,161],"first":[77],"stage,":[78],"an":[79],"extensive":[80],"image-text":[81],"RS-Control":[85,114],"created":[87],"prompt":[89],"engineering":[90],"multimodal":[92],"large":[93],"language":[94],"(MLLMs)":[96],"manual":[98],"prompts":[99],"for":[100,135],"existing":[101],"datasets,":[102,138],"incorporates":[103],"diverse":[104],"conditional":[105],"controls":[106],"with":[107],"rich":[108],"information.":[112],"Then":[113],"utilized":[117],"train":[119],"universal":[121,133],"model.":[125],"The":[126],"second":[127],"stage":[128],"involves":[129],"efficient":[130],"tuning":[131],"different":[136],"minimizing":[139],"fine-tuning":[140],"costs":[141],"while":[142],"preserving":[143],"diversity":[144],"high-quality":[146],"features.":[147],"Experiments":[148],"conducted":[149],"on":[150],"RSICD":[152],"caption":[153],"WHU":[156],"change":[157],"detection":[158],"demonstrate":[160],"superiority":[162],"over":[165],"other":[166],"state-of-the-art":[167],"generation.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}