{"id":"https://openalex.org/W3167539120","doi":"https://doi.org/10.1109/cvpr46437.2021.01574","title":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","display_name":"To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3167539120","doi":"https://doi.org/10.1109/cvpr46437.2021.01574","mag":"3167539120"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.01574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.01574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5079961895","display_name":"Yuning Chai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yuning Chai","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060736311","display_name":"Pei Sun","orcid":"https://orcid.org/0000-0002-4651-6227"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pei Sun","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045825594","display_name":"Jiquan Ngiam","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiquan Ngiam","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102747545","display_name":"Weiyue Wang","orcid":"https://orcid.org/0000-0002-8114-8271"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Weiyue Wang","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008894717","display_name":"Benjamin Caine","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Caine","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004650249","display_name":"Vijay Vasudevan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Vasudevan","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320910","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-9101-3565"},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081024054","display_name":"Dragomir Anguelov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145145","display_name":"Nomor Research (Germany)","ror":"https://ror.org/04727qm97","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210145145"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dragomir Anguelov","raw_affiliation_strings":["Waymo LLC"],"affiliations":[{"raw_affiliation_string":"Waymo LLC","institution_ids":["https://openalex.org/I4210145145"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5079961895"],"corresponding_institution_ids":["https://openalex.org/I4210145145"],"apc_list":null,"apc_paid":null,"fwci":66.1535,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.99857977,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15995","last_page":"16004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.998199999332428,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7264693975448608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769707798957825},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6059851050376892},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5633720755577087},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5116255879402161},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4902105927467346},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4644607901573181},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4351325035095215},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.43252283334732056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.298248827457428},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27422666549682617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20750373601913452},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2053142488002777}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7264693975448608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769707798957825},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6059851050376892},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5633720755577087},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5116255879402161},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4902105927467346},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4644607901573181},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4351325035095215},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.43252283334732056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.298248827457428},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27422666549682617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20750373601913452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2053142488002777},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.01574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.01574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1920022804","https://openalex.org/W1923184257","https://openalex.org/W2150066425","https://openalex.org/W2415454270","https://openalex.org/W2560609797","https://openalex.org/W2594519801","https://openalex.org/W2624273542","https://openalex.org/W2896457183","https://openalex.org/W2897529137","https://openalex.org/W2935837427","https://openalex.org/W2949708697","https://openalex.org/W2963083779","https://openalex.org/W2963120444","https://openalex.org/W2963121255","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963727135","https://openalex.org/W2964062501","https://openalex.org/W2968296999","https://openalex.org/W2970259716","https://openalex.org/W2979750740","https://openalex.org/W2981440248","https://openalex.org/W2988715931","https://openalex.org/W3030520226","https://openalex.org/W3031752193","https://openalex.org/W3034314779","https://openalex.org/W3035172746","https://openalex.org/W3035574168","https://openalex.org/W3103351485","https://openalex.org/W3106250896","https://openalex.org/W3107212734","https://openalex.org/W3117901461","https://openalex.org/W3208394352","https://openalex.org/W4385245566","https://openalex.org/W4394671432","https://openalex.org/W6639824700","https://openalex.org/W6640300118","https://openalex.org/W6687484953","https://openalex.org/W6739663239","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6760424586","https://openalex.org/W6763422710","https://openalex.org/W6766799972","https://openalex.org/W6769571200","https://openalex.org/W6771941581","https://openalex.org/W6775796324","https://openalex.org/W6778129325","https://openalex.org/W6778485988","https://openalex.org/W6780673685","https://openalex.org/W6781239247","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2337415362","https://openalex.org/W121273120","https://openalex.org/W2740820121","https://openalex.org/W317572212","https://openalex.org/W2002009170","https://openalex.org/W2922421953","https://openalex.org/W2034462085","https://openalex.org/W3002270006","https://openalex.org/W2141888456","https://openalex.org/W4312857205"],"abstract_inverted_index":{"3D":[0,23,44],"object":[1],"detection":[2,144],"is":[3,150],"vital":[4],"for":[5,142],"many":[6],"robotics":[7],"applications.":[8],"For":[9],"tasks":[10],"where":[11],"a":[12,22,36,83],"2D":[13,37],"perspective":[14,124],"range":[15,28,125],"image":[16,29,126],"exists,":[17],"we":[18,34],"propose":[19],"to":[20,87,147],"learn":[21],"representation":[24],"directly":[25],"from":[26,145],"this":[27,32],"view.":[30,127],"To":[31],"end,":[33],"designed":[35],"convolutional":[38],"network":[39,100],"architecture":[40],"that":[41,154],"carries":[42],"the":[43,51,64,71,88,102,104,107,116,123,133,139,161],"spherical":[45],"coordinates":[46],"of":[47,63],"each":[48,76],"pixel":[49],"throughout":[50],"network.":[52],"Its":[53],"layers":[54],"can":[55],"consume":[56],"any":[57],"arbitrary":[58],"convolution":[59],"kernel":[60,68,85],"in":[61,122,153,164],"place":[62],"default":[65],"inner":[66],"product":[67],"and":[69,91,106,137,171],"exploit":[70],"underlying":[72],"local":[73],"geometry":[74],"around":[75],"pixel.":[77],"We":[78,110],"outline":[79],"four":[80],"such":[81],"kernels:":[82],"dense":[84],"according":[86],"bag-of-words":[89],"paradigm,":[90],"three":[92],"graph":[93,98],"kernels":[94],"inspired":[95],"by":[96,120],"recent":[97],"neural":[99],"advances:":[101],"Transformer,":[103],"PointNet,":[105],"Edge":[108],"Convolution.":[109],"also":[111,151],"explore":[112],"cross-modality":[113],"fusion":[114],"with":[115],"camera":[117],"image,":[118],"facilitated":[119],"operating":[121],"Our":[128],"method":[129],"performs":[130],"competitively":[131],"on":[132],"Waymo":[134],"Open":[135],"Dataset":[136],"improves":[138],"state-of-the-art":[140],"AP":[141],"pedestrian":[143],"69.7%":[146],"75.5%.":[148],"It":[149],"efficient":[152],"our":[155],"smallest":[156],"model,":[157],"which":[158],"still":[159],"outperforms":[160],"popular":[162],"PointPillars":[163],"quality,":[165],"requires":[166],"180":[167],"times":[168],"fewer":[169],"FLOPS":[170],"model":[172],"parameters.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":16}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}