{"id":"https://openalex.org/W7124426014","doi":"https://doi.org/10.1109/tmm.2026.3654407","title":"LLMI3D: MLLM-Based 3D Perception From a Single 2D Image","display_name":"LLMI3D: MLLM-Based 3D Perception From a Single 2D Image","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124426014","doi":"https://doi.org/10.1109/tmm.2026.3654407"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3654407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654407","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5123218668","display_name":"Fan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["School of Software, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5810-9226","affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123213136","display_name":"Sicheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Zhao","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5843-6411","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123177808","display_name":"Yanhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107425","display_name":"Healthpoint","ror":"https://ror.org/01ncapf89","country_code":"AE","type":"healthcare","lineage":["https://openalex.org/I4210107425"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Yanhao Zhang","raw_affiliation_strings":["OPPO AI Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center, Beijing, China","institution_ids":["https://openalex.org/I4210107425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123179661","display_name":"Hui Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Chen","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4180-5801","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007720098","display_name":"H. Lu","orcid":"https://orcid.org/0000-0001-6332-2785"},"institutions":[{"id":"https://openalex.org/I4210107425","display_name":"Healthpoint","ror":"https://ror.org/01ncapf89","country_code":"AE","type":"healthcare","lineage":["https://openalex.org/I4210107425"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center, Beijing, China","institution_ids":["https://openalex.org/I4210107425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605531","display_name":"Jungong Han","orcid":"https://orcid.org/0000-0003-4361-956X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4361-956X","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105838441","display_name":"Guiguang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiguang Ding","raw_affiliation_strings":["School of Software, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0137-9975","affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06225646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3838","last_page":"3852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7491000294685364,"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":0.7491000294685364,"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":0.055799998342990875,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03220000118017197,"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/perception","display_name":"Perception","score":0.566100001335144},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5622000098228455},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5604000091552734},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5047000050544739},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.4742000102996826},{"id":"https://openalex.org/keywords/3d-modeling","display_name":"3D modeling","score":0.42340001463890076},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.38029998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6783000230789185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3654407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3654407","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5391899347305298,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G2365988345","display_name":null,"funder_award_id":"62525103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G338250432","display_name":null,"funder_award_id":"62441235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4144755178","display_name":null,"funder_award_id":"62571294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6036694980","display_name":null,"funder_award_id":"L252009","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G7091651887","display_name":null,"funder_award_id":"62021002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,28,41,46],"autonomous":[3],"driving,":[4],"augmented":[5],"reality,":[6],"robotics,":[7],"and":[8,62,76,100,134,160],"embodied":[9],"intelligence":[10],"have":[11,125],"necessitated":[12],"3D":[13,18,47,52,87,91,103,121],"perception":[14,19],"algorithms.":[15],"However,":[16],"current":[17],"methods,":[20],"especially":[21],"specialized":[22],"small":[23],"models,":[24,159],"exhibit":[25],"poor":[26,57],"generalization":[27],"open":[29],"scenarios.":[30],"On":[31],"the":[32,78,113,127],"other":[33,147],"hand,":[34],"multimodal":[35],"large":[36,151],"language":[37],"models":[38],"(MLLMs)":[39],"excel":[40],"general":[42],"capacity":[43],"but":[44],"underperform":[45],"tasks,":[48],"due":[49],"to":[50,64,115],"weak":[51],"local":[53],"spatial":[54,88],"object":[55],"perception,":[56],"text-based":[58],"geometric":[59,98],"numerical":[60],"output,":[61],"inability":[63],"handle":[65],"camera":[66,107],"focal":[67,108],"variations.":[68,110],"To":[69],"address":[70],"these":[71],"challenges,":[72],"we":[73,124],"develop":[74],"LLMI3D,":[75],"propose":[77],"following":[79],"solutions:":[80],"Spatial-Enhanced":[81],"Local":[82],"Feature":[83],"Mining":[84],"for":[85,96,105,119],"better":[86],"feature":[89],"extraction,":[90],"Query":[92],"Token-Derived":[93],"Info":[94],"Decoding":[95],"precise":[97],"regression,":[99],"Geometry":[101],"Projection-Based":[102],"Reasoning":[104],"handling":[106],"length":[109],"We":[111,153],"are":[112],"first":[114],"adapt":[116],"an":[117],"MLLM":[118],"image-based":[120],"perception.":[122],"Additionally,":[123],"constructed":[126],"IG3D":[128],"dataset,":[129],"which":[130],"provides":[131],"fine-grained":[132],"descriptions":[133],"question-answer":[135],"annotations.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"that":[140],"our":[141,157],"LLMI3D":[142],"achieves":[143],"state-of-the-art":[144],"performance,":[145],"outperforming":[146],"methods":[148],"by":[149],"a":[150],"margin.":[152],"will":[154],"publicly":[155],"release":[156],"code,":[158],"dataset.":[161]},"counts_by_year":[],"updated_date":"2026-05-26T06:15:08.310788","created_date":"2026-01-17T00:00:00"}