{"id":"https://openalex.org/W4416241513","doi":"https://doi.org/10.1109/wacv61042.2026.00678","title":"VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics","display_name":"VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416241513","doi":"https://doi.org/10.1109/wacv61042.2026.00678"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.07744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035572125","display_name":"Daniel Cher","orcid":"https://orcid.org/0000-0002-3747-7879"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Cher","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058002611","display_name":"Biaobiao Wei","orcid":"https://orcid.org/0009-0008-6513-556X"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Wei","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089378935","display_name":"Srikumar Sastry","orcid":"https://orcid.org/0000-0002-4646-9416"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikumar Sastry","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029557305","display_name":"Nathan Jacobs","orcid":"https://orcid.org/0000-0002-4242-8967"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Jacobs","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00968957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7019","last_page":"7029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.34689998626708984,"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":0.34689998626708984,"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":0.08460000157356262,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.06360000371932983,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6657999753952026},{"id":"https://openalex.org/keywords/polygon","display_name":"Polygon (computer graphics)","score":0.6435999870300293},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5059000253677368},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47999998927116394},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4410000145435333},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.4058000147342682},{"id":"https://openalex.org/keywords/satellite-image","display_name":"Satellite image","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C190694206","wikidata":"https://www.wikidata.org/wiki/Q3276654","display_name":"Polygon (computer graphics)","level":3,"score":0.6435999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501000285148621},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C2985301230","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite image","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2985999882221222},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.07744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07744","pdf_url":"https://arxiv.org/pdf/2511.07744","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.07744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.07744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.07744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.07744","pdf_url":"https://arxiv.org/pdf/2511.07744","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,116],"introduce":[1],"VectorSynth,":[2],"a":[3,56,96],"diffusion-based":[4],"framework":[5,60],"for":[6],"pixel-accurate":[7],"satellite":[8,99],"image":[9,58],"synthesis":[10],"conditioned":[11],"on":[12],"polygonal":[13],"geographic":[14],"annotations":[15,105],"with":[16,77,102,110],"semantic":[17,34,67,124],"attributes.":[18],"Unlike":[19],"prior":[20,121],"text-":[21],"or":[22],"layout-conditioned":[23],"models,":[24],"VectorSynth":[25,69],"learns":[26],"dense":[27],"cross-modal":[28],"correspondences":[29],"that":[30,73,131],"align":[31],"imagery":[32],"and":[33,66,86,92,113,126,129,143],"vector":[35],"geometry,":[36],"enabling":[37],"fine-grained,":[38],"spatially":[39],"grounded":[40],"edits.":[41],"A":[42],"vision":[43,134],"language":[44,75,135],"alignment":[45],"module":[46],"produces":[47],"pixel-level":[48],"embeddings":[49,54],"from":[50],"polygon":[51,104],"semantics;":[52],"these":[53],"guide":[55],"conditional":[57],"generation":[59],"to":[61],"respect":[62],"both":[63,111],"spatial":[64,84,139],"extents":[65],"cues.":[68],"supports":[70],"interactive":[71],"workflows":[72],"mix":[74],"prompts":[76],"geometry-aware":[78],"conditioning,":[79],"allowing":[80],"rapid":[81],"what-if":[82],"simulations,":[83],"edits,":[85],"map-informed":[87],"content":[88],"generation.":[89],"For":[90],"training":[91],"evaluation,":[93],"we":[94],"assemble":[95],"collection":[97],"of":[98],"scenes":[100,109],"paired":[101],"pixel-registered":[103],"spanning":[106],"diverse":[107],"urban":[108],"built":[112],"natural":[114],"features.":[115],"observe":[117],"strong":[118],"improvements":[119],"over":[120],"methods":[122],"in":[123],"fidelity":[125],"structural":[127],"realism,":[128],"show":[130],"our":[132],"trained":[133],"model":[136],"demonstrates":[137],"fine-grained":[138],"grounding.":[140],"The":[141],"code":[142],"data":[144],"are":[145],"available":[146],"at":[147],"https://github.com/mvrl/VectorSynth.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-13T00:00:00"}