{"id":"https://openalex.org/W4416214739","doi":"https://doi.org/10.1109/lra.2025.3632759","title":"MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction","display_name":"MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214739","doi":"https://doi.org/10.1109/lra.2025.3632759"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3632759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3632759","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5079932099","display_name":"Zhiqiang Wei","orcid":"https://orcid.org/0000-0002-2830-8301"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiqiang Wei","raw_affiliation_strings":["School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100296529","display_name":"Lianqing Zheng","orcid":"https://orcid.org/0000-0002-7186-4055"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianqing Zheng","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100637677","display_name":"Jianan Liu","orcid":"https://orcid.org/0009-0002-7179-0129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianan Liu","raw_affiliation_strings":["Momoni AI, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Momoni AI, Gothenburg, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767738","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-8098-8906"},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["College of Science and Engineering, James Cook University, Cairns, QLD, Australia"],"affiliations":[{"raw_affiliation_string":"College of Science and Engineering, James Cook University, Cairns, QLD, Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083874423","display_name":"Qing\u2010Long Han","orcid":"https://orcid.org/0000-0002-7207-0716"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qing-Long Han","raw_affiliation_strings":["School of Engineering, Swinburne University of Technology, Melbourne, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Swinburne University of Technology, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103107425","display_name":"Wenwen Zhang","orcid":"https://orcid.org/0000-0002-9767-2959"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenwen Zhang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038544469","display_name":"Fengdeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengdeng Zhang","raw_affiliation_strings":["School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I148128674"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5079932099"],"corresponding_institution_ids":["https://openalex.org/I148128674"],"apc_list":null,"apc_paid":null,"fwci":1.2784,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85773038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":"1","first_page":"370","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5444999933242798,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5444999933242798,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.16099999845027924,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.07639999687671661,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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/voxel","display_name":"Voxel","score":0.6169999837875366},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.3944000005722046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.362199991941452},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.358599990606308},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3538999855518341},{"id":"https://openalex.org/keywords/occupancy-grid-mapping","display_name":"Occupancy grid mapping","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6952999830245972},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C57077369","wikidata":"https://www.wikidata.org/wiki/Q7075747","display_name":"Occupancy grid mapping","level":4,"score":0.33730000257492065},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3632759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3632759","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2795587607","https://openalex.org/W2897529137","https://openalex.org/W2963727135","https://openalex.org/W2991216808","https://openalex.org/W3008115128","https://openalex.org/W3035574168","https://openalex.org/W3108426750","https://openalex.org/W3109395584","https://openalex.org/W3126856052","https://openalex.org/W3129529899","https://openalex.org/W3174692508","https://openalex.org/W3215584334","https://openalex.org/W4226236972","https://openalex.org/W4312357798","https://openalex.org/W4312707458","https://openalex.org/W4382464460","https://openalex.org/W4385318467","https://openalex.org/W4386066358","https://openalex.org/W4386075910","https://openalex.org/W4386083035","https://openalex.org/W4390872638","https://openalex.org/W4390873564","https://openalex.org/W4390874155","https://openalex.org/W4390874310","https://openalex.org/W4390874817","https://openalex.org/W4394708612","https://openalex.org/W4401414288","https://openalex.org/W4402186962","https://openalex.org/W4402307972","https://openalex.org/W4402713134","https://openalex.org/W4404005296","https://openalex.org/W4404725701","https://openalex.org/W4405219754","https://openalex.org/W4409262980"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"3D":[1],"semantic":[2,30,59,108,140],"occupancy":[3],"perception":[4,216],"is":[5,50],"essential":[6],"for":[7,227],"autonomous":[8,230],"driving":[9,231],"in":[10,141,214],"complex":[11],"environments":[12],"with":[13,56,96,107],"diverse":[14],"and":[15,47,100,166,179,220],"irregular":[16],"objects.":[17],"While":[18],"vision-centric":[19],"methods":[20],"suffer":[21],"from":[22],"geometric":[23,54,98],"inaccuracies,":[24],"LiDAR-based":[25],"approaches":[26],"often":[27],"lack":[28],"rich":[29],"information.":[31],"To":[32],"address":[33],"these":[34],"limitations,":[35],"MS-Occ,":[36],"a":[37,167,190],"novel":[38],"multi-stage":[39],"LiDAR-camera":[40],"fusion":[41,46],"framework":[42,66],"which":[43],"includes":[44],"middle-stage":[45,76],"late-stage":[48,116],"fusion,":[49,78,118],"proposed,":[51],"integrating":[52],"LiDAR's":[53],"fidelity":[55],"camera":[57],"based":[58],"richness":[60],"via":[61,110],"hierarchical":[62],"cross-modal":[63],"fusion.":[64],"The":[65],"introduces":[67],"innovations":[68],"at":[69],"two":[70,148],"critical":[71,229],"stages:":[72],"(1)":[73],"In":[74,114],"the":[75,79,101,115,119,131,174,184,205,215,222],"feature":[77],"Gaussian-Geo":[80],"module":[81,103,123,138],"leverages":[82],"Gaussian":[83],"kernel":[84],"rendering":[85],"on":[86,147,183],"sparse":[87],"LiDAR":[88,105],"depth":[89],"maps":[90],"to":[91],"enhance":[92],"2D":[93],"image":[94],"features":[95,127],"dense":[97],"priors,":[99],"Semantic-Aware":[102],"enriches":[104],"voxels":[106],"context":[109],"deformable":[111],"cross-attention;":[112],"(2)":[113],"voxel":[117,126],"Adaptive":[120],"Fusion":[121,136],"(AF)":[122],"dynamically":[124],"balances":[125],"across":[128],"modalities,":[129],"while":[130],"High":[132],"Classification":[133],"Confidence":[134],"Voxel":[135],"(HCCVF)":[137],"resolves":[139],"consistencies":[142],"using":[143],"self-attention-based":[144],"refinement.":[145],"Experiments":[146],"large-scale":[149],"benchmarks":[150],"demonstrate":[151],"state-of-the-art":[152,175,192],"per":[153],"formance.":[154],"On":[155],"nuScenes-OpenOccupancy,":[156],"MS-Occ":[157,226],"achieves":[158,189],"an":[159],"Intersection":[160],"over":[161],"Union":[162],"(IoU)":[163],"of":[164,171,194,207,217,225],"32.1%":[165],"mean":[168],"IoU":[169,178],"(mIoU)":[170],"25.3%,":[172],"surpassing":[173],"by":[176],"+0.7%":[177],"+2.4%":[180],"mIoU.":[181],"Furthermore,":[182],"SemanticKITTI":[185],"benchmark,":[186],"our":[187],"method":[188],"new":[191],"mIoU":[193],"24.08%,":[195],"robustly":[196],"validating":[197],"its":[198],"generalization":[199],"capabilities.":[200],"Ablation":[201],"studies":[202],"further":[203],"confirm":[204],"effectiveness":[206],"each":[208],"individual":[209],"module,":[210],"highlighting":[211],"substantial":[212],"improvements":[213],"small":[218],"objects":[219],"reinforcing":[221],"practical":[223],"value":[224],"safety":[228],"scenarios.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-14T00:00:00"}