{"id":"https://openalex.org/W4414270461","doi":"https://doi.org/10.1109/lra.2025.3611145","title":"Efficient Multi-Camera Tokenization With Triplanes for End-to-End Driving","display_name":"Efficient Multi-Camera Tokenization With Triplanes for End-to-End Driving","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4414270461","doi":"https://doi.org/10.1109/lra.2025.3611145"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3611145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3611145","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/A5091869385","display_name":"Boris Ivanovic","orcid":"https://orcid.org/0000-0002-8698-202X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boris Ivanovic","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8698-202X","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079316363","display_name":"Cristiano Saltori","orcid":"https://orcid.org/0000-0001-9583-4160"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristiano Saltori","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069174793","display_name":"Yurong You","orcid":"https://orcid.org/0000-0002-6898-9463"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yurong You","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6898-9463","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905406","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-0322-8479"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073600541","display_name":"Wenjie Luo","orcid":"https://orcid.org/0000-0002-2070-465X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenjie Luo","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0206-4337","affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091869385"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82551707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"10","issue":"11","first_page":"11713","last_page":"11720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9957000017166138,"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":0.9957000017166138,"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/T13579","display_name":"Image and Video Stabilization","score":0.9868999719619751,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/inference","display_name":"Inference","score":0.589900016784668},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5859000086784363},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5673999786376953},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5196999907493591},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.49399998784065247},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.38280001282691956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620999813079834},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5673999786376953},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33970001339912415},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3611145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3611145","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2962785568","https://openalex.org/W2963627347","https://openalex.org/W3035574168","https://openalex.org/W3094502228","https://openalex.org/W3109585842","https://openalex.org/W3180355996","https://openalex.org/W3184957317","https://openalex.org/W3215769467","https://openalex.org/W4312453532","https://openalex.org/W4313021454","https://openalex.org/W4385245566","https://openalex.org/W4385430679","https://openalex.org/W4386075614","https://openalex.org/W4386075787","https://openalex.org/W4386076275","https://openalex.org/W4386076400","https://openalex.org/W4386083035","https://openalex.org/W4390872423","https://openalex.org/W4390873312","https://openalex.org/W4401386967","https://openalex.org/W4402727317","https://openalex.org/W4402754007","https://openalex.org/W4402772377","https://openalex.org/W4405632633","https://openalex.org/W4413146794"],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"Transformers":[1],"are":[2,73],"increasingly":[3],"being":[4],"deployed":[5],"as":[6],"end-to-end":[7],"robot":[8],"and":[9,19,66,81,98,138],"autonomous":[10],"vehicle":[11],"(AV)":[12],"policy":[13,128],"architectures,":[14],"owing":[15],"to":[16,21,36,68,75,118,125],"their":[17,82,88],"scalability":[18],"potential":[20],"leverage":[22],"internet-scale":[23],"pretraining":[24],"for":[25,87],"generalization.":[26],"Accordingly,":[27],"tokenizing":[28],"sensor":[29,70],"data":[30],"<italic":[31],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">efficiently</i>":[33],"is":[34],"paramount":[35],"ensuring":[37],"the":[38,76,132],"real-time":[39],"feasibility":[40],"of":[41,78],"such":[42],"architectures":[43],"on":[44,94],"embedded":[45],"hardware.":[46],"To":[47],"this":[48],"end,":[49],"we":[50],"present":[51],"an":[52,91],"efficient":[53],"triplane-based":[54],"multi-camera":[55],"tokenization":[56,114],"strategy":[57],"that":[58,72,104],"leverages":[59],"recent":[60],"advances":[61],"in":[62,123,142],"3D":[63],"neural":[64,101],"reconstruction":[65],"rendering":[67],"produce":[69],"tokens":[71],"agnostic":[74],"number":[77],"input":[79],"cameras":[80],"resolution,":[83],"while":[84,130],"explicitly":[85],"accounting":[86],"geometry":[89],"around":[90],"AV.":[92],"Experiments":[93],"large-scale":[95],"AV":[96],"datasets":[97],"a":[99],"state-of-the-art":[100],"simulator":[102],"demonstrate":[103],"our":[105],"approach":[106],"yields":[107],"significant":[108],"savings":[109],"over":[110],"current":[111],"image":[112],"patch-based":[113],"strategies,":[115],"producing":[116],"up":[117,124],"72%":[119],"fewer":[120],"tokens,":[121],"resulting":[122],"50%":[126],"faster":[127],"inference":[129],"achieving":[131],"same":[133],"open-loop":[134],"motion":[135],"planning":[136],"accuracy":[137],"improved":[139],"offroad":[140],"rates":[141],"closed-loop":[143],"driving":[144],"simulations.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}