{"id":"https://openalex.org/W4416513696","doi":"https://doi.org/10.1109/iccv51701.2025.00908","title":"GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields","display_name":"GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416513696","doi":"https://doi.org/10.1109/iccv51701.2025.00908"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/2506.23352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113140398","display_name":"Shunsuke Yasuki","orcid":null},"institutions":[{"id":"https://openalex.org/I133557312","display_name":"Rikkyo University","ror":"https://ror.org/00x194q47","country_code":"JP","type":"education","lineage":["https://openalex.org/I133557312"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shunsuke Yasuki","raw_affiliation_strings":["Rikkyo University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rikkyo University","institution_ids":["https://openalex.org/I133557312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006630406","display_name":"Taiki Miyanishi","orcid":"https://orcid.org/0000-0001-9105-1601"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taiki Miyanishi","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041272440","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0000-0002-9761-4142"},"institutions":[{"id":"https://openalex.org/I4210085920","display_name":"Shanghai Institute for Science of Science","ror":"https://ror.org/004srxn73","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210085920"]},{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Institute of Science Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo","institution_ids":["https://openalex.org/I4210085920","https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073732915","display_name":"Shuhei Kurita","orcid":"https://orcid.org/0000-0001-7415-3120"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuhei Kurita","raw_affiliation_strings":["National Institute of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102058289","display_name":"Koya Sakamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koya Sakamoto","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031443776","display_name":"Daichi Azuma","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Azuma","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084053028","display_name":"Masato Taki","orcid":"https://orcid.org/0000-0002-5375-7862"},"institutions":[{"id":"https://openalex.org/I133557312","display_name":"Rikkyo University","ror":"https://ror.org/00x194q47","country_code":"JP","type":"education","lineage":["https://openalex.org/I133557312"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Taki","raw_affiliation_strings":["Rikkyo University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rikkyo University","institution_ids":["https://openalex.org/I133557312"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074059447","display_name":"Yutaka Matsuo","orcid":"https://orcid.org/0000-0002-2070-4393"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Matsuo","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5113140398"],"corresponding_institution_ids":["https://openalex.org/I133557312"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33567977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9737","last_page":"9748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8841000199317932,"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":0.8841000199317932,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.023800000548362732,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.019700000062584877,"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/spatial-intelligence","display_name":"Spatial intelligence","score":0.5899999737739563},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5236999988555908},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5234000086784363},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49970000982284546},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4812000095844269},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.4465000033378601},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4239000082015991},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.37130001187324524},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.3693999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007000088691711},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31940001249313354},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23352","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23352","pdf_url":"https://arxiv.org/pdf/2506.23352","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23352","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:2506.23352","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23352","pdf_url":"https://arxiv.org/pdf/2506.23352","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7749669166","display_name":null,"funder_award_id":"25K03177","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G83763464","display_name":null,"funder_award_id":"JPMJPR22P8","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,208],"advancement":[1],"of":[2,61],"3D":[3,11,57,69,78,179,203],"language":[4,125,180],"fields":[5,181],"has":[6],"enabled":[7],"intuitive":[8],"interactions":[9,53],"with":[10,54,85],"scenes":[12],"via":[13,205],"natural":[14,51,206],"language.":[15,207],"However,":[16],"existing":[17,178],"approaches":[18],"are":[19],"typically":[20],"limited":[21],"to":[22,80,131],"small-scale":[23],"environments,":[24],"lacking":[25],"the":[26,193],"scalability":[27],"and":[28,101,104,118,135,170,182],"compositional":[29,197],"reasoning":[30,129,199],"capabilities":[31],"necessary":[32],"for":[33,88],"large,":[34],"complex":[35],"urban":[36,92],"settings.":[37],"To":[38,144,188],"overcome":[39],"these":[40],"limitations,":[41],"we":[42,150],"propose":[43],"GeoProg3D,":[44],"a":[45,66,75,153],"visual":[46],"programming":[47],"framework":[48,122,195],"that":[49,73,174],"enables":[50],"language-driven":[52],"city-scale":[55,148,202],"high-fidelity":[56,201],"scenes.":[58],"GeoProg3D":[59,175,191],"consists":[60],"two":[62],"key":[63],"components:":[64],"(i)":[65],"Geography-aware":[67],"City-scale":[68],"Language":[70],"Field":[71],"(GCLF)":[72],"leverages":[74],"memory-efficient":[76],"hierarchical":[77],"model":[79],"handle":[81],"large-scale":[82],"data,":[83,100],"integrated":[84],"geographic":[86,111,141,198],"information":[87],"efficiently":[89],"filtering":[90],"vast":[91],"spaces":[93],"using":[94],"directional":[95],"cues,":[96],"distance":[97],"measurements,":[98],"elevation":[99],"landmark":[102],"references;":[103],"(ii)":[105],"Geographical":[106],"Vision":[107],"APIs":[108],"(GV-APIs),":[109],"specialized":[110],"vision":[112,142],"tools":[113],"such":[114],"as":[115,128],"area":[116],"segmentation":[117],"object":[119],"detection.":[120],"Our":[121],"employs":[123],"large":[124],"models":[126,184],"(LLMs)":[127],"engines":[130],"dynamically":[132],"combine":[133],"GV-APIs":[134],"operate":[136],"GCLF,":[137],"effectively":[138],"supporting":[139],"diverse":[140],"tasks.":[143,187],"assess":[145],"performance":[146],"in":[147,200],"reasoning,":[149,167],"introduce":[151],"GeoEval3D,":[152],"comprehensive":[154],"benchmark":[155],"dataset":[156],"containing":[157],"952":[158],"query-answer":[159],"pairs":[160],"across":[161,185],"five":[162],"challenging":[163],"tasks:":[164],"grounding,":[165],"spatial":[166],"comparison,":[168],"counting,":[169],"measurement.":[171],"Experiments":[172],"demonstrate":[173],"significantly":[176],"outperforms":[177],"vision-language":[183],"multiple":[186],"our":[189],"knowledge,":[190],"is":[192,210],"first":[194],"enabling":[196],"environments":[204],"code":[209],"available":[211],"at":[212],"https://snskysk.github.io/GeoProg3D/.":[213]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}