{"id":"https://openalex.org/W4310078553","doi":"https://doi.org/10.1007/s11263-022-01710-9","title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","display_name":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4310078553","doi":"https://doi.org/10.1007/s11263-022-01710-9"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-022-01710-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01710-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01710-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01710-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083443210","display_name":"Shaoshuai Shi","orcid":"https://orcid.org/0000-0003-2558-181X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE","HK"],"is_corresponding":true,"raw_author_name":"Shaoshuai Shi","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-2558-181X","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392353","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0001-7058-6957"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE","HK"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407596","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-0597-4475"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101981769","display_name":"Chaoxu Guo","orcid":"https://orcid.org/0000-0001-8715-4827"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxu Guo","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125510","display_name":"Jianping Shi","orcid":"https://orcid.org/0000-0003-3257-8272"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Shi","raw_affiliation_strings":["SenseTime Research, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444820","display_name":"Xiaogang Wang","orcid":"https://orcid.org/0000-0002-7929-5889"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083443210"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I4210109712"],"apc_list":{"value":3690,"currency":"USD","value_usd":3690},"apc_paid":{"value":3690,"currency":"USD","value_usd":3690},"fwci":35.0519,"has_fulltext":true,"cited_by_count":505,"citation_normalized_percentile":{"value":0.99881127,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"131","issue":"2","first_page":"531","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.769070565700531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7032561898231506},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.61836838722229},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5537770390510559},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5227779746055603},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.48442819714546204},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.476790189743042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47321194410324097},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.4576323330402374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37856072187423706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13975098729133606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769070565700531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7032561898231506},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.61836838722229},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5537770390510559},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5227779746055603},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.48442819714546204},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.476790189743042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47321194410324097},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.4576323330402374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37856072187423706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13975098729133606},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-022-01710-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01710-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01710-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-022-01710-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-022-01710-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-022-01710-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310078553.pdf","grobid_xml":"https://content.openalex.org/works/W4310078553.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2150066425","https://openalex.org/W2193145675","https://openalex.org/W2229637417","https://openalex.org/W2468368736","https://openalex.org/W2555618208","https://openalex.org/W2560544142","https://openalex.org/W2565639579","https://openalex.org/W2605189827","https://openalex.org/W2788158258","https://openalex.org/W2798965597","https://openalex.org/W2897529137","https://openalex.org/W2949708697","https://openalex.org/W2951517617","https://openalex.org/W2954174912","https://openalex.org/W2960986959","https://openalex.org/W2962807143","https://openalex.org/W2963037989","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2963231572","https://openalex.org/W2963351448","https://openalex.org/W2963400571","https://openalex.org/W2963517242","https://openalex.org/W2963667201","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2964166085","https://openalex.org/W2968296999","https://openalex.org/W2972211064","https://openalex.org/W2979750740","https://openalex.org/W2981949127","https://openalex.org/W2988715931","https://openalex.org/W2990613095","https://openalex.org/W2991084087","https://openalex.org/W2999947750","https://openalex.org/W3003618643","https://openalex.org/W3004237909","https://openalex.org/W3004351857","https://openalex.org/W3008105217","https://openalex.org/W3010797203","https://openalex.org/W3017930107","https://openalex.org/W3034236957","https://openalex.org/W3034314779","https://openalex.org/W3034407526","https://openalex.org/W3035172746","https://openalex.org/W3035346742","https://openalex.org/W3035461736","https://openalex.org/W3035749845","https://openalex.org/W3106250896","https://openalex.org/W3107212734","https://openalex.org/W3107819843","https://openalex.org/W3108426750","https://openalex.org/W3109395584","https://openalex.org/W3109646990","https://openalex.org/W3109675406","https://openalex.org/W3114509423","https://openalex.org/W3117804044","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3171377125","https://openalex.org/W3173668541","https://openalex.org/W3175563878","https://openalex.org/W3205005447","https://openalex.org/W4214777292","https://openalex.org/W4225793049","https://openalex.org/W4312894406","https://openalex.org/W4382464460","https://openalex.org/W4390872833","https://openalex.org/W6601473709","https://openalex.org/W6601977772"],"related_works":["https://openalex.org/W3027020613","https://openalex.org/W2016533837","https://openalex.org/W3167885074","https://openalex.org/W2892386716","https://openalex.org/W1998563493","https://openalex.org/W4306164210","https://openalex.org/W4313316311","https://openalex.org/W4362608745","https://openalex.org/W2969228573","https://openalex.org/W2963690996"],"abstract_inverted_index":{"Abstract":[0],"3D":[1,33,44,50,96,158],"object":[2,34,97],"detection":[3,35,51,159,176],"is":[4,134],"receiving":[5],"increasing":[6],"attention":[7],"from":[8],"both":[9,60],"industry":[10],"and":[11,64,78,94,114,164],"academia":[12],"thanks":[13],"to":[14],"its":[15],"wide":[16],"applications":[17],"in":[18],"various":[19],"fields.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,40,85],"propose":[25,41,86],"Point-Voxel":[26],"Region-based":[27],"Convolution":[28],"Neural":[29],"Networks":[30],"(PV-RCNNs)":[31],"for":[32,91,108,117],"on":[36,161,174],"point":[37,121],"clouds.":[38],"First,":[39],"a":[42],"novel":[43,70],"detector,":[45],"PV-RCNN,":[46,142],"which":[47],"boosts":[48],"the":[49,56,74,79,162,175],"performance":[52,160],"by":[53],"deeply":[54],"integrating":[55],"feature":[57,82],"learning":[58],"of":[59,101,178],"point-based":[61],"set":[62],"abstraction":[63],"voxel-based":[65],"sparse":[66],"convolution":[67],"through":[68],"two":[69,102,130],"steps,":[71],"i.e.":[72],",":[73],"voxel-to-keypoint":[75],"scene":[76],"encoding":[77],"keypoint-to-grid":[80],"RoI":[81],"abstraction.":[83],"Second,":[84],"an":[87],"advanced":[88],"framework,":[89],"PV-RCNN++,":[90],"more":[92,111],"efficient":[93],"accurate":[95],"detection.":[98],"It":[99],"consists":[100],"major":[103],"improvements:":[104],"sectorized":[105],"proposal-centric":[106],"sampling":[107],"efficiently":[109],"producing":[110],"representative":[112],"keypoints,":[113],"VectorPool":[115],"aggregation":[116],"better":[118,146],"aggregating":[119],"local":[120],"features":[122],"with":[123,169],"much":[124],"less":[125],"resource":[126],"consumption.":[127],"With":[128],"these":[129],"strategies,":[131],"our":[132,152],"PV-RCNN++":[133,154],"about":[135],"$$3\\times":[136],"$$":[137],"<mml:math":[138,182],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>3</mml:mn><mml:mo>\u00d7</mml:mo></mml:mrow></mml:math>":[139],"faster":[140],"than":[141],"while":[143],"also":[144],"achieving":[145],"performance.":[147],"The":[148],"experiments":[149],"demonstrate":[150],"that":[151],"proposed":[153],"framework":[155],"achieves":[156],"state-of-the-art":[157],"large-scale":[163],"highly-competitive":[165],"Waymo":[166],"Open":[167],"Dataset":[168],"10":[170],"FPS":[171],"inference":[172],"speed":[173],"range":[177],"$$150m":[179],"\\times":[180],"150m$$":[181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mn>150</mml:mn><mml:mi>m</mml:mi><mml:mo>\u00d7</mml:mo><mml:mn>150</mml:mn><mml:mi>m</mml:mi></mml:mrow></mml:math>":[183],".":[184]},"counts_by_year":[{"year":2026,"cited_by_count":63},{"year":2025,"cited_by_count":164},{"year":2024,"cited_by_count":126},{"year":2023,"cited_by_count":115},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":11}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}