{"id":"https://openalex.org/W7138095948","doi":"https://doi.org/10.1609/aaai.v40i10.37791","title":"LLaVA\u00b3: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs","display_name":"LLaVA\u00b3: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138095948","doi":"https://doi.org/10.1609/aaai.v40i10.37791"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37791","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37791","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37791/41753","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37791/41753","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113407728","display_name":"Doriand Petit","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Doriand Petit","raw_affiliation_strings":["CEA List\nIRIT, Universit\u00e9 de Toulouse"],"affiliations":[{"raw_affiliation_string":"CEA List\nIRIT, Universit\u00e9 de Toulouse","institution_ids":["https://openalex.org/I4210085861","https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I17866349","https://openalex.org/I4210119061","https://openalex.org/I2738703131","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129644318","display_name":"Steve Bourgeois","orcid":null},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Steve Bourgeois","raw_affiliation_strings":["CEA List"],"affiliations":[{"raw_affiliation_string":"CEA List","institution_ids":["https://openalex.org/I4210085861","https://openalex.org/I2738703131"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706351","display_name":"Vincent Gay-Bellile","orcid":null},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Gay-Bellile","raw_affiliation_strings":["CEA List"],"affiliations":[{"raw_affiliation_string":"CEA List","institution_ids":["https://openalex.org/I4210085861","https://openalex.org/I2738703131"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028134242","display_name":"Florian Chabot","orcid":null},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florian Chabot","raw_affiliation_strings":["CEA List"],"affiliations":[{"raw_affiliation_string":"CEA List","institution_ids":["https://openalex.org/I4210085861","https://openalex.org/I2738703131"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129671942","display_name":"Lo\u00efc Barthe","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lo\u00efc Barthe","raw_affiliation_strings":["IRIT, Universit\u00e9 de Toulouse"],"affiliations":[{"raw_affiliation_string":"IRIT, Universit\u00e9 de Toulouse","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I17866349","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113407728"],"corresponding_institution_ids":["https://openalex.org/I134560555","https://openalex.org/I17866349","https://openalex.org/I2738703131","https://openalex.org/I3131550300","https://openalex.org/I4210085861","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39222874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8412","last_page":"8420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9882000088691711,"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":0.9882000088691711,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010000000474974513,"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/viewpoints","display_name":"Viewpoints","score":0.6510999798774719},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5853000283241272},{"id":"https://openalex.org/keywords/3d-model","display_name":"3d model","score":0.5023000240325928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.492000013589859},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.43560001254081726},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.39910000562667847},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.39469999074935913}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.718500018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027000188827515},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6139000058174133},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5853000283241272},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37791","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37791","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37791/41753","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37791","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37791","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37791/41753","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138095948.pdf","grobid_xml":"https://content.openalex.org/works/W7138095948.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Developing":[0],"a":[1,43,74,78],"multi-modal":[2],"language":[3,121],"model":[4],"capable":[5],"of":[6,17,26,53,73,96,109],"understanding":[7,51],"3D":[8,18,49,75,87,107,115,120],"scenes":[9],"remains":[10],"challenging":[11],"due":[12],"to":[13,23,84],"the":[14,24,48,86,90,110],"limited":[15],"availability":[16],"training":[19],"data,":[20],"in":[21],"contrast":[22],"abundance":[25],"2D":[27,58,80],"datasets":[28],"used":[29],"for":[30,89],"vision-language":[31],"models":[32],"(VLMs).":[33],"As":[34],"an":[35,104],"alternative,":[36],"we":[37,82],"introduce":[38],"LLaVA\u00b3":[39],"(pronounced":[40],"LLaVA":[41],"Cube),":[42],"novel":[44],"method":[45],"that":[46,124],"improves":[47],"scene":[50,88],"capabilities":[52],"VLMs":[54],"using":[55],"only":[56],"multi-view":[57,106],"images,":[59],"and":[60,119],"without":[61],"requiring":[62],"any":[63],"fine-tuning.":[64],"Inspired":[65],"by":[66],"Cubist":[67],"painters,":[68],"who":[69],"represented":[70],"multiple":[71],"viewpoints":[72],"object":[76],"within":[77],"single":[79],"picture,":[81],"propose":[83],"describe":[85],"VLM":[91,131],"through":[92],"omnidirectional":[93],"visual":[94,116],"representations":[95,100],"each":[97],"object.":[98],"These":[99],"are":[101],"derived":[102],"from":[103],"intermediate":[105],"reconstruction":[108],"scene.":[111],"Extensive":[112],"experiments":[113],"on":[114],"question":[117],"answering":[118],"grounding":[122],"show":[123],"our":[125],"approach":[126],"significantly":[127],"outperforms":[128],"previous":[129],"2D-based":[130],"solutions.":[132]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2026-03-18T00:00:00"}
