{"id":"https://openalex.org/W4405792509","doi":"https://doi.org/10.1109/iccv51701.2025.00831","title":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","display_name":"3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405792509","doi":"https://doi.org/10.1109/iccv51701.2025.00831"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00831","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.18450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058209276","display_name":"Tatiana Zemskova","orcid":"https://orcid.org/0000-0003-4271-7336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatiana Zemskova","raw_affiliation_strings":["AIRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025655729","display_name":"Dmitry Yudin","orcid":"https://orcid.org/0000-0002-1407-2633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Yudin","raw_affiliation_strings":["AIRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00140193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8885","last_page":"8895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9921000003814697,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9921000003814697,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9907000064849854,"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":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6712749004364014},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49129360914230347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3973408639431}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6712749004364014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49129360914230347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3973408639431}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00831","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:2412.18450","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.18450","pdf_url":"https://arxiv.org/pdf/2412.18450","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.18450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.18450","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:2412.18450","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.18450","pdf_url":"https://arxiv.org/pdf/2412.18450","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7738218999","display_name":null,"funder_award_id":"139-15-2025-013","funder_id":"https://openalex.org/F4320330091","funder_display_name":"Moscow Institute of Physics and Technology"}],"funders":[{"id":"https://openalex.org/F4320324632","display_name":"Ministero dello Sviluppo Economico","ror":"https://ror.org/011z3ff80"},{"id":"https://openalex.org/F4320330091","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405792509.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"A":[0],"3D":[1,53,88,134,152],"scene":[2,7,78,135],"graph":[3,136],"represents":[4],"a":[5,23,43,125,129,133],"compact":[6],"model":[8],"by":[9],"capturing":[10],"both":[11],"the":[12,16,51,87,93,113],"objects":[13],"present":[14],"and":[15,71,111,164],"semantic":[17,115,140,178],"relationships":[18,116,179],"between":[19,117,180],"them,":[20],"making":[21],"it":[22],"promising":[24],"structure":[25],"for":[26,62,76,127,150],"robotic":[27],"applications.":[28],"To":[29],"effectively":[30],"interact":[31],"with":[32],"users,":[33],"an":[34],"embodied":[35],"intelligent":[36],"agent":[37],"should":[38],"be":[39],"able":[40],"to":[41,66,86,148],"answer":[42],"wide":[44],"range":[45],"of":[46,95,132],"natural":[47,68],"language":[48,69],"queries":[49],"about":[50],"surrounding":[52],"environment.":[54],"Large":[55],"Language":[56],"Models":[57],"(LLMs)":[58],"are":[59],"beneficial":[60],"solutions":[61],"user-robot":[63],"interaction":[64],"due":[65],"their":[67],"understanding":[70],"reasoning":[72],"abilities.":[73],"Recent":[74],"methods":[75,100],"learning":[77],"representations":[79,85],"have":[80],"shown":[81],"that":[82,137,169,174],"adapting":[83],"these":[84],"world":[89],"can":[90],"significantly":[91],"improve":[92],"quality":[94],"LLM":[96],"responses.":[97],"However,":[98],"existing":[99],"typically":[101],"rely":[102],"only":[103],"on":[104,158],"geometric":[105],"information,":[106],"such":[107],"as":[108,146],"object":[109],"coordinates,":[110],"overlook":[112],"rich":[114],"objects.":[118,181],"In":[119,155],"this":[120],"work,":[121],"we":[122,167],"propose":[123],"3DGraphLLM,":[124],"method":[126],"constructing":[128],"learnable":[130],"representation":[131,143],"explicitly":[138],"incorporates":[139],"relationships.":[141],"This":[142],"is":[144,184],"used":[145],"input":[147],"LLMs":[149],"performing":[151],"vision-language":[153],"tasks.":[154],"our":[156,170],"experiments":[157],"popular":[159],"ScanRefer,":[160],"Multi3DRefer,":[161],"ScanQA,":[162],"Sqa3D,":[163],"Scan2cap":[165],"datasets,":[166],"demonstrate":[168],"approach":[171],"outperforms":[172],"baselines":[173],"do":[175],"not":[176],"leverage":[177],"The":[182],"code":[183],"publicly":[185],"available":[186],"at":[187],"https://github.com/CognitiveAISystems/3DGraphLLM.":[188]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}