{"id":"https://openalex.org/W7154743403","doi":"https://doi.org/10.1109/tip.2026.3683282","title":"Multi-View Images Suffice 3D Reasoning Through Chain-of-Thought Selection and Question-Guided Fusion","display_name":"Multi-View Images Suffice 3D Reasoning Through Chain-of-Thought Selection and Question-Guided Fusion","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154743403","doi":"https://doi.org/10.1109/tip.2026.3683282","pmid":"https://pubmed.ncbi.nlm.nih.gov/41996434"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3683282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3683282","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5024163072","display_name":"Boqiang Xu","orcid":"https://orcid.org/0000-0003-1465-5553"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqiang Xu","raw_affiliation_strings":["Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1465-5553","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020280128","display_name":"Jianmin Wu","orcid":"https://orcid.org/0000-0002-0999-9194"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlin Wu","raw_affiliation_strings":["Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences (CASIA), Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133895507","display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133903627","display_name":"Chenyang Su","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Su","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112582835","display_name":"Jian Liang","orcid":"https://orcid.org/0000-0003-3890-1894"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liang","raw_affiliation_strings":["New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3890-1894","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103779396","display_name":"Z X Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenan Sun","raw_affiliation_strings":["New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-9935","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition and the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109299788","display_name":"Zhen Lei","orcid":"https://orcid.org/0000-0002-0791-189X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Lei","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0791-189X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.48996982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"4122","last_page":"4133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1340000033378601,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1340000033378601,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.12839999794960022,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.10019999742507935,"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/selection","display_name":"Selection (genetic algorithm)","score":0.6017000079154968},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4855000078678131},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4796000123023987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.40459999442100525},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.38850000500679016},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7109000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.569599986076355},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4796000123023987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.38850000500679016},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3683282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3683282","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41996434","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41996434","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5137853622436523}],"awards":[{"id":"https://openalex.org/G1004037439","display_name":null,"funder_award_id":"62306313","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4103426291","display_name":null,"funder_award_id":"U2441251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5181136371","display_name":null,"funder_award_id":"62276256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8525382974","display_name":null,"funder_award_id":"U1836217","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,17,29,44,158,169,185],"reasoning":[1,30,39,109],"is":[2],"crucial":[3],"in":[4,157],"areas":[5],"like":[6],"robotics":[7],"and":[8,97,195,203,208],"autonomous":[9],"driving.":[10],"Due":[11],"to":[12,24,27,43,61,113,155],"the":[13,36,62,73,102,106,150,168,177],"high":[14],"cost":[15],"of":[16,41,87,111,127,179],"data":[18],"acquisition,":[19],"some":[20],"recent":[21],"methods":[22,48,199],"attempt":[23],"enable":[25],"LLMs":[26,42,112,152],"perform":[28],"through":[31,161,172],"multi-view":[32,70,116,141,162,173],"images,":[33,174],"thereby":[34],"transferring":[35],"powerful":[37,107],"2D":[38],"capabilities":[40,110],"environments.":[45],"However,":[46],"these":[47,79],"face":[49],"challenges:":[50],"either":[51],"they":[52,65],"use":[53],"redundant":[54],"views":[55],"that":[56],"contain":[57],"many":[58],"perspectives":[59],"irrelevant":[60],"question,":[63],"or":[64,183],"rely":[66],"on":[67,206],"globally":[68],"aggregated":[69],"representations,":[71],"losing":[72],"fine-grained":[74],"vision-language":[75],"correlations.":[76],"To":[77],"tackle":[78],"challenges,":[80],"we":[81,133],"propose":[82,134],"3DMulti-LLM,":[83],"which":[84],"mainly":[85],"consists":[86],"three":[88],"components:":[89],"a":[90,93,124,135],"COT":[91,103],"selector,":[92],"question-guided":[94,136,144],"fusion":[95,137],"block,":[96],"pre-trained":[98,151],"LLMs.":[99],"Specifically,":[100],"first,":[101],"selector":[104],"leverages":[105],"chain-of-thought":[108],"identify":[114],"question-related":[115],"images.":[117],"In":[118],"this":[119],"way,":[120],"3DMulti-LLM":[121,191],"can":[122],"eliminate":[123],"substantial":[125],"amount":[126],"interference":[128],"from":[129],"unnecessary":[130],"viewpoints.":[131,148],"Then,":[132],"block":[138],"for":[139],"integrating":[140],"features":[142],"via":[143],"interaction":[145],"among":[146],"various":[147],"Finally,":[149],"are":[153],"utilized":[154],"reason":[156],"scenes":[159],"directly":[160],"features.":[163],"Notably,":[164],"our":[165,189],"approach":[166],"understands":[167],"scene":[170],"solely":[171],"without":[175],"requiring":[176],"input":[178],"point":[180],"cloud":[181],"information":[182],"additional":[184],"feature":[186],"extraction.":[187],"Through":[188],"experiments,":[190],"achieves":[192],"impressive":[193],"performance":[194],"surpasses":[196],"existing":[197],"3D-input-free":[198],"by":[200],"+":[201,204],"12.2%":[202],"7.1%":[205],"ScanQA":[207],"3DMV-VQA":[209],"datasets,":[210],"respectively.":[211]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-18T00:00:00"}