{"id":"https://openalex.org/W7114993177","doi":"https://doi.org/10.1145/3757374.3771534","title":"AeroVis3R: Geometry-Aware Vision\u2013Language Models for 3D Reasoning over UAV Landmark Videos","display_name":"AeroVis3R: Geometry-Aware Vision\u2013Language Models for 3D Reasoning over UAV Landmark Videos","publication_year":2025,"publication_date":"2025-12-13","ids":{"openalex":"https://openalex.org/W7114993177","doi":"https://doi.org/10.1145/3757374.3771534"},"language":null,"primary_location":{"id":"doi:10.1145/3757374.3771534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757374.3771534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Posters","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":null,"display_name":"Cewen Deng","orcid":"https://orcid.org/0009-0004-3162-5668"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I2800531931","display_name":"Hong Kong College of Technology","ror":"https://ror.org/014w0p014","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800531931"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Cewen Deng","raw_affiliation_strings":["HKUST, Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0004-3162-5668","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2800531931","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I2800531931","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59549937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6646999716758728,"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":0.6646999716758728,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0494999997317791,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0340999998152256,"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/landmark","display_name":"Landmark","score":0.7900999784469604},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5281000137329102},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3953999876976013},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.3700999915599823},{"id":"https://openalex.org/keywords/3d-model","display_name":"3d model","score":0.2912999987602234},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2847000062465668}],"concepts":[{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7900999784469604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528000235557556},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6309999823570251},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2556999921798706},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757374.3771534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757374.3771534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Posters","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Unmanned":[0],"aerial":[1],"vehicles":[2],"(UAVs)":[3],"enable":[4],"scalable":[5],"capture":[6],"of":[7,74],"cultural":[8],"landmarks,":[9],"yet":[10],"monocular":[11],"video":[12,100],"alone":[13],"remains":[14],"geometrically":[15],"ambiguous":[16],"and":[17,46,60,104],"difficult":[18],"for":[19],"language":[20],"models":[21],"to":[22,116],"interpret.":[23],"We":[24],"present":[25],"AeroVis3R,":[26],"a":[27,71],"unified":[28],"framework":[29],"that":[30,53,97],"couples":[31],"geometric":[32],"reconstruction":[33],"with":[34,58,79],"multimodal":[35,95,122],"reasoning.":[36],"Our":[37],"system":[38],"reconstructs":[39],"dense":[40],"3D":[41,102],"structures":[42],"from":[43],"UAV":[44,99],"videos":[45,77],"distills":[47],"them":[48],"into":[49,88],"compact":[50],"geometry":[51,87],"representations":[52],"can":[54],"be":[55,110],"jointly":[56],"processed":[57],"visual":[59],"textual":[61,82],"inputs.":[62],"To":[63],"support":[64],"research":[65],"in":[66,120],"this":[67],"direction,":[68],"we":[69],"collect":[70],"new":[72],"dataset":[73,108],"92":[75],"landmark":[76],"paired":[78],"automatically":[80],"aligned":[81],"descriptions.":[83],"By":[84],"integrating":[85],"explicit":[86],"the":[89],"reasoning":[90],"process,":[91],"AeroVis3R":[92],"achieves":[93],"geometry-grounded":[94],"understanding":[96],"bridges":[98],"capture,":[101],"reconstruction,":[103],"language-based":[105],"analysis.":[106],"The":[107],"will":[109],"made":[111],"publicly":[112],"available":[113],"upon":[114],"acceptance":[115],"encourage":[117],"further":[118],"advances":[119],"geometry-aware":[121],"learning.":[123]},"counts_by_year":[],"updated_date":"2025-12-13T23:15:11.045004","created_date":"2025-12-13T00:00:00"}