{"id":"https://openalex.org/W4414956203","doi":"https://doi.org/10.1109/tcsvt.2025.3619211","title":"MVFormer: UNet-Like Transformer With Mix-Voxel Attention for Camera-Based 3D Semantic Scene Completion","display_name":"MVFormer: UNet-Like Transformer With Mix-Voxel Attention for Camera-Based 3D Semantic Scene Completion","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4414956203","doi":"https://doi.org/10.1109/tcsvt.2025.3619211"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3619211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3619211","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5107720789","display_name":"Feixiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feixiang Gao","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","College of Mechanical and Vehicle Engineering, Chongqing University, China"],"raw_orcid":"https://orcid.org/0009-0000-7706-4334","affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680371","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0002-1282-0204"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","College of Mechanical and Vehicle Engineering, Chongqing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628775","display_name":"Ke Wang","orcid":"https://orcid.org/0000-0002-0797-4655"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Wang","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","College of Mechanical and Vehicle Engineering, Chongqing University, China"],"raw_orcid":"https://orcid.org/0000-0002-0797-4655","affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438327","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0001-5681-9937"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhou","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","College of Mechanical and Vehicle Engineering, Chongqing University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021950355","display_name":"Jianbo L\u01da","orcid":"https://orcid.org/0000-0001-9088-5663"},"institutions":[{"id":"https://openalex.org/I4210131005","display_name":"Chery Automobile (China)","ror":"https://ror.org/02xab7z06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210131005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbo Lu","raw_affiliation_strings":["Dynamics Research Laboratory, Geely Automobile Research Institute (Ningbo) Company Ltd., Ningbo, Zhejiang, China","Dynamics Research Laboratory, Geely Automobile Research Institute (Ningbo) Co., Ltd., Ningbo, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-9088-5663","affiliations":[{"raw_affiliation_string":"Dynamics Research Laboratory, Geely Automobile Research Institute (Ningbo) Company Ltd., Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210131005"]},{"raw_affiliation_string":"Dynamics Research Laboratory, Geely Automobile Research Institute (Ningbo) Co., Ltd., Ningbo, Zhejiang, China","institution_ids":["https://openalex.org/I4210131005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19581547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"4004","last_page":"4015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9973999857902527,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962999820709229,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/semantics","display_name":"Semantics (computer science)","score":0.6162999868392944},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5174000263214111},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48660001158714294},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.45719999074935913},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4307999908924103},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42489999532699585},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.35830000042915344},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721999883651733},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629000067710876},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5174000263214111},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5144000053405762},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48660001158714294},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3619211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3619211","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G340695466","display_name":null,"funder_award_id":"52372408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8086880677","display_name":null,"funder_award_id":"CSTB2023TIAD-STX0029","funder_id":"https://openalex.org/F4320336740","funder_display_name":"Chongqing Municipality Key Research and Development Program 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/F4320336740","display_name":"Chongqing Municipality Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2557465155","https://openalex.org/W2963307292","https://openalex.org/W2991216808","https://openalex.org/W3034868495","https://openalex.org/W3035308182","https://openalex.org/W3118453581","https://openalex.org/W3126856052","https://openalex.org/W3173727695","https://openalex.org/W3174692508","https://openalex.org/W3195680177","https://openalex.org/W3215584334","https://openalex.org/W4226270845","https://openalex.org/W4318829201","https://openalex.org/W4385245566","https://openalex.org/W4386066358","https://openalex.org/W4386071535","https://openalex.org/W4386083035","https://openalex.org/W4386524555","https://openalex.org/W4389726103","https://openalex.org/W4390872682","https://openalex.org/W4390873564","https://openalex.org/W4390874310","https://openalex.org/W4391305584","https://openalex.org/W4399019097","https://openalex.org/W4401070061","https://openalex.org/W4402676329","https://openalex.org/W4402727359","https://openalex.org/W4402727581","https://openalex.org/W4402753672","https://openalex.org/W4402891997","https://openalex.org/W4405429367","https://openalex.org/W4405785635","https://openalex.org/W4406171243","https://openalex.org/W4406433346","https://openalex.org/W4407128129","https://openalex.org/W4407351641","https://openalex.org/W4408071484","https://openalex.org/W4409261950","https://openalex.org/W4409427161","https://openalex.org/W4412030548","https://openalex.org/W7133220049"],"related_works":[],"abstract_inverted_index":{"3D":[0,10],"Semantic":[1],"Scene":[2],"Completion":[3],"(3D":[4],"SSC),":[5],"aiming":[6],"to":[7,55,72,117],"infer":[8],"complete":[9],"scene":[11,64],"geometry":[12,59],"and":[13,23,60,83,87,130,144],"semantics":[14,61],"from":[15,65],"partial":[16],"observations,":[17],"is":[18],"crucial":[19],"for":[20,90],"autonomous":[21],"driving":[22],"robotics.":[24],"Recent":[25],"progress":[26],"in":[27],"SSC":[28],"has":[29,36],"leveraged":[30],"the":[31,50,57,109,150,154],"Transformer":[32,107],"architecture,":[33],"while":[34,147],"UNet":[35,110],"shown":[37],"strong":[38],"multi-scale":[39,115,123],"feature":[40,120,124],"aggregation":[41],"capabilities.":[42],"Building":[43],"on":[44,127],"these,":[45],"we":[46],"propose":[47],"MVFormer,":[48],"integrating":[49,106],"strengths":[51],"of":[52,62,141,153],"both":[53],"architectures":[54],"predict":[56],"dense":[58],"a":[63,96,100],"2D":[66,74],"images.":[67],"MVFormer":[68,134],"utilizes":[69],"depth":[70],"information":[71,89,116],"separate":[73],"image":[75],"features,":[76],"improving":[77],"object":[78],"representation":[79],"at":[80,161],"varying":[81],"distances,":[82],"providing":[84],"rich":[85],"geometric":[86],"semantic":[88],"voxel":[91,119],"initialization.":[92],"We":[93],"also":[94],"introduce":[95],"UNet-like":[97],"decoder":[98,113],"with":[99,138],"novel":[101],"Mix-Voxel":[102],"attention":[103],"mechanism,":[104],"seamlessly":[105],"into":[108],"structure.":[111],"This":[112],"uses":[114],"guide":[118],"updates,":[121],"enhancing":[122],"capture.":[125],"Experiments":[126],"SemanticKITTI,":[128],"SSCBench-KITTI-360":[129],"NYUv2":[131],"show":[132],"that":[133],"achieves":[135],"state-of-the-art":[136],"performance,":[137],"mIoU":[139],"scores":[140],"15.81%,":[142],"18.94%":[143],"32.96%":[145],"respectively,":[146],"significantly":[148],"reducing":[149],"computational":[151],"complexity":[152],"model.":[155],"The":[156],"code":[157],"will":[158],"be":[159],"available":[160],"https://github.com/Ricardovvvv/MVFormer.":[162]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}