{"id":"https://openalex.org/W4403791765","doi":"https://doi.org/10.1145/3664647.3681257","title":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","display_name":"MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791765","doi":"https://doi.org/10.1145/3664647.3681257"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101956627","display_name":"Yuan Tang","orcid":"https://orcid.org/0000-0001-6772-9427"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Tang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6772-9427","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982575","display_name":"Xu Han","orcid":"https://orcid.org/0009-0009-1966-2585"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-1966-2585","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763339","display_name":"Xianzhi Li","orcid":"https://orcid.org/0000-0001-6835-5607"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianzhi Li","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6835-5607","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051958442","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-6392-9461"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Yu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-6392-9461","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040872496","display_name":"Yixue Hao","orcid":"https://orcid.org/0000-0001-7296-2522"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixue Hao","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7296-2522","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101909898","display_name":"Long Hu","orcid":"https://orcid.org/0000-0001-6496-6793"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Hu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6496-6793","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337209","display_name":"Min Chen","orcid":"https://orcid.org/0000-0002-0960-4447"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Chen","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0960-4447","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9301,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.96585219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6617","last_page":"6626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9986000061035156,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9955000281333923,"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":0.9933000206947327,"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/prior-probability","display_name":"Prior probability","score":0.7940390706062317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7218465805053711},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6340306997299194},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5054547786712646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38302022218704224},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11722290515899658},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11112138628959656},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06030210852622986}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7940390706062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218465805053711},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6340306997299194},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5054547786712646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38302022218704224},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11722290515899658},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11112138628959656},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06030210852622986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681257","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2600463316","https://openalex.org/W3119866685","https://openalex.org/W4212774754","https://openalex.org/W4221143046","https://openalex.org/W4234552385","https://openalex.org/W4287121196","https://openalex.org/W4287391717","https://openalex.org/W4312270234","https://openalex.org/W4383108457","https://openalex.org/W4386075660","https://openalex.org/W4394862732","https://openalex.org/W4394862768","https://openalex.org/W6796487566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2580650124","https://openalex.org/W4386190339","https://openalex.org/W2968424575","https://openalex.org/W3142333283","https://openalex.org/W3122088529","https://openalex.org/W3041320102","https://openalex.org/W2111669074"],"abstract_inverted_index":{"Large":[0,11],"2D":[1,98,108],"vision-language":[2],"models":[3,29],"(2D-LLMs)":[4],"have":[5],"gained":[6],"significant":[7],"attention":[8],"by":[9,22],"bridging":[10],"Language":[12],"Models":[13],"(LLMs)":[14],"with":[15,42,95,138,180],"images":[16],"using":[17,97],"a":[18,115,124,128],"simple":[19],"projector.":[20],"Inspired":[21],"their":[23],"success,":[24],"large":[25],"3D":[26,92,110,174],"point":[27,33,40,93],"cloud-language":[28],"(3D-LLMs)":[30],"also":[31],"integrate":[32],"clouds":[34,41,94],"into":[35],"LLMs.":[36],"However,":[37],"directly":[38],"aligning":[39],"LLM":[43],"requires":[44],"expensive":[45],"training":[46,78,118,183],"costs,":[47],"typically":[48],"in":[49,123,152],"hundreds":[50],"of":[51,59,130],"GPU-hours":[52,210],"on":[53,83,173,191,211],"A100,":[54],"which":[55,102,157],"hinders":[56],"the":[57,105,196,205,216,220,227],"development":[58],"3D-LLMs.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,88,142],"introduce":[65,114],"MiniGPT-3D,":[66],"an":[67,188],"efficient":[68,221],"and":[69,109,127,148,177,230],"powerful":[70],"3D-LLM":[71],"that":[72,169],"achieves":[73,171],"multiple":[74],"SOTA":[75,172],"results":[76],"while":[77,204],"for":[79,120,195],"only":[80,153],"27":[81],"hours":[82],"one":[84],"RTX":[85],"3090.":[86],"Specifically,":[87],"propose":[89],"to":[90,134,160,202,218,226],"align":[91],"LLMs":[96],"priors":[99],"from":[100],"2D-LLMs,":[101],"can":[103],"leverage":[104],"similarity":[106],"between":[107],"visual":[111],"information.":[112],"We":[113,214],"novel":[116],"four-stage":[117],"strategy":[119],"modality":[121],"alignment":[122],"cascaded":[125],"way,":[126],"mixture":[129],"query":[131],"experts":[132],"module":[133],"adaptively":[135],"aggregate":[136],"features":[137],"high":[139],"efficiency.":[140],"Moreover,":[141],"utilize":[143],"parameter-efficient":[144],"fine-tuning":[145],"methods":[146],"LoRA":[147],"Norm":[149],"fine-tuning,":[150],"resulting":[151],"47.8M":[154],"learnable":[155],"parameters,":[156],"is":[158],"up":[159],"260x":[161],"fewer":[162],"than":[163],"existing":[164],"methods.":[165],"Extensive":[166],"experiments":[167],"show":[168],"MiniGPT-3D":[170,186],"object":[175,198],"classification":[176],"captioning":[178,199],"tasks,":[179],"significantly":[181],"cheaper":[182],"costs.":[184],"Notably,":[185],"gains":[187],"8.12":[189],"increase":[190],"GPT-4":[192],"evaluation":[193],"score":[194],"challenging":[197],"task":[200],"compared":[201],"ShapeLLM-13B,":[203],"latter":[206],"costs":[207],"160":[208],"total":[209],"8":[212],"A800.":[213],"are":[215,232],"first":[217],"explore":[219],"3D-LLM,":[222],"offering":[223],"new":[224],"insights":[225],"community.":[228],"Code":[229],"weights":[231],"available":[233],"at":[234],"https://github.com/TangYuan96/MiniGPT-3D.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}