{"id":"https://openalex.org/W7124940626","doi":"https://doi.org/10.1109/cbmi66578.2025.11339286","title":"Breaking the 2D Dependency: What Limits 3D-Only Open-Vocabulary Scene Understanding","display_name":"Breaking the 2D Dependency: What Limits 3D-Only Open-Vocabulary Scene Understanding","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124940626","doi":"https://doi.org/10.1109/cbmi66578.2025.11339286"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5038933961","display_name":"Domenico D'orsi","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Domenico D'Orsi","raw_affiliation_strings":["University of Pisa,Dept. of Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa,Dept. of Computer Engineering,Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121131835","display_name":"Fabio Carrara","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Carrara","raw_affiliation_strings":["CNR-ISTI,Pisa,Italy"],"affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fabrizio Falchi","orcid":null},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Falchi","raw_affiliation_strings":["CNR-ISTI,Pisa,Italy"],"affiliations":[{"raw_affiliation_string":"CNR-ISTI,Pisa,Italy","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123429940","display_name":"Nicola Tonellotto","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa,Dept. of Computer Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa,Dept. of Computer Engineering,Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038933961"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69113313,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4410000145435333,"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":0.4410000145435333,"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":0.17710000276565552,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0737999975681305,"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/robustness","display_name":"Robustness (evolution)","score":0.7411999702453613},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5878000259399414},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4745999872684479},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41589999198913574}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7411999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467000246047974},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7863954305648804}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2594519801","https://openalex.org/W3109585842","https://openalex.org/W4206453737","https://openalex.org/W4312270234","https://openalex.org/W4312649925","https://openalex.org/W4313036632","https://openalex.org/W4385318467","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386075705","https://openalex.org/W4386076097","https://openalex.org/W4390872744","https://openalex.org/W4402727529","https://openalex.org/W4402727761","https://openalex.org/W4402961820","https://openalex.org/W4403889366"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"3D":[1,10,73,114],"scene":[2],"understanding,":[3],"i.e.,":[4],"recognizing":[5],"and":[6,27,63,139,153],"classifying":[7],"objects":[8],"in":[9,45],"scenes":[11],"without":[12],"being":[13],"limited":[14],"to":[15,40,136,157],"a":[16,22,53,100,147],"predefined":[17],"set":[18],"of":[19,52,96,112,150,161],"classes,":[20],"is":[21,155],"foundational":[23],"task":[24],"for":[25,118],"robotics":[26],"extended":[28],"reality":[29],"applications.":[30],"Current":[31],"leading":[32],"methods":[33],"often":[34],"rely":[35],"on":[36,60,79],"2D":[37,61],"foundation":[38],"models":[39,62,115],"extract":[41],"semantics,":[42],"then":[43],"projected":[44],"3D.":[46],"This":[47],"paper":[48],"investigates":[49],"the":[50,109,124,128,159],"viability":[51],"purely":[54],"3D-native":[55,89,163],"pipeline,":[56],"thereby":[57],"eliminating":[58],"dependencies":[59],"reprojections.":[64],"We":[65,122,144],"systematically":[66],"explored":[67],"various":[68],"architectural":[69],"combinations":[70],"using":[71],"established":[72],"components.":[74],"However,":[75],"our":[76],"extensive":[77],"experiments":[78],"benchmark":[80],"datasets":[81],"reveal":[82],"significant":[83],"performance":[84,92],"limitations":[85,130],"with":[86,91],"this":[87],"direct":[88],"approach,":[90],"metrics":[93],"falling":[94],"short":[95],"expectations.":[97],"Rather":[98],"than":[99],"simple":[101],"failure,":[102],"these":[103],"outcomes":[104],"provide":[105],"critical":[106],"insights":[107],"into":[108],"current":[110],"deficiencies":[111],"existing":[113],"when":[116],"cascaded":[117],"complex":[119],"open-vocabulary":[120,164],"tasks.":[121],"highlight":[123],"lessons":[125],"learned,":[126],"identify":[127],"pipeline's":[129],"(e.g.,":[131],"segmenter-encoder":[132],"domain":[133],"gap,":[134],"robustness":[135],"imperfect":[137],"segmentations),":[138],"posit":[140],"future":[141],"research":[142],"directions.":[143],"argue":[145],"that":[146],"fundamental":[148],"rethinking":[149],"model":[151],"design":[152],"interplay":[154],"necessary":[156],"realize":[158],"potential":[160],"truly":[162],"understanding.":[165]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-21T00:00:00"}
