{"id":"https://openalex.org/W3167071962","doi":"https://doi.org/10.1109/cvpr46437.2021.00815","title":"Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models","display_name":"Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3167071962","doi":"https://doi.org/10.1109/cvpr46437.2021.00815","mag":"3167071962"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr46437.2021.00815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00815","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/A5009409073","display_name":"Benjamin Eckart","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Benjamin Eckart","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058911745","display_name":"Wentao Yuan","orcid":"https://orcid.org/0000-0002-3836-8877"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wentao Yuan","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755357","display_name":"Chao Liu","orcid":"https://orcid.org/0000-0001-7261-3832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Liu","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056503617","display_name":"Jan Kautz","orcid":"https://orcid.org/0000-0002-8830-429X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Kautz","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009409073"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.2817,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.99128787,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8244","last_page":"8253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.9983000159263611,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7199215888977051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6464275121688843},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5843207240104675},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5468827486038208},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5428838729858398},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5287280082702637},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5098504424095154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.485074907541275},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4735656976699829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4681439995765686},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.434389591217041},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4205201268196106},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.29561182856559753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199215888977051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6464275121688843},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5843207240104675},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5468827486038208},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5428838729858398},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5287280082702637},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5098504424095154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.485074907541275},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4735656976699829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4681439995765686},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.434389591217041},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4205201268196106},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29561182856559753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr46437.2021.00815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr46437.2021.00815","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1561952261","https://openalex.org/W1920022804","https://openalex.org/W1959608418","https://openalex.org/W2021122545","https://openalex.org/W2056898157","https://openalex.org/W2071906076","https://openalex.org/W2099471712","https://openalex.org/W2133844819","https://openalex.org/W2187089797","https://openalex.org/W2190691619","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2338532005","https://openalex.org/W2460657278","https://openalex.org/W2519887557","https://openalex.org/W2546066744","https://openalex.org/W2560609797","https://openalex.org/W2594519801","https://openalex.org/W2745471877","https://openalex.org/W2784996692","https://openalex.org/W2785325870","https://openalex.org/W2796426482","https://openalex.org/W2842511635","https://openalex.org/W2850910281","https://openalex.org/W2896457183","https://openalex.org/W2944828972","https://openalex.org/W2949671016","https://openalex.org/W2952263313","https://openalex.org/W2963090522","https://openalex.org/W2963121255","https://openalex.org/W2963125977","https://openalex.org/W2963341956","https://openalex.org/W2963443993","https://openalex.org/W2963641970","https://openalex.org/W2963855530","https://openalex.org/W2964015378","https://openalex.org/W2964137676","https://openalex.org/W2970160935","https://openalex.org/W2979750740","https://openalex.org/W2981995220","https://openalex.org/W2986615800","https://openalex.org/W2990789488","https://openalex.org/W2991216808","https://openalex.org/W3005680577","https://openalex.org/W3010623357","https://openalex.org/W3011537551","https://openalex.org/W3034459762","https://openalex.org/W3034781633","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036982689","https://openalex.org/W3045125647","https://openalex.org/W3091695563","https://openalex.org/W3096538374","https://openalex.org/W3096655658","https://openalex.org/W3100859887","https://openalex.org/W3109154950","https://openalex.org/W3109585842","https://openalex.org/W3116959466","https://openalex.org/W3128716822","https://openalex.org/W4288623616","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W4394671432","https://openalex.org/W6610566761","https://openalex.org/W6633448084","https://openalex.org/W6640300118","https://openalex.org/W6640963894","https://openalex.org/W6687484953","https://openalex.org/W6700872662","https://openalex.org/W6703199735","https://openalex.org/W6704170123","https://openalex.org/W6726873649","https://openalex.org/W6729001083","https://openalex.org/W6739778489","https://openalex.org/W6747899497","https://openalex.org/W6748208425","https://openalex.org/W6752996450","https://openalex.org/W6754967834","https://openalex.org/W6755056417","https://openalex.org/W6755207826","https://openalex.org/W6762573206","https://openalex.org/W6763103765","https://openalex.org/W6763422710","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6779977557","https://openalex.org/W6780515965","https://openalex.org/W6784270828","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W2726367589","https://openalex.org/W2440023763","https://openalex.org/W2962474440","https://openalex.org/W60493759","https://openalex.org/W4308619659","https://openalex.org/W4311117049","https://openalex.org/W3213069564"],"abstract_inverted_index":{"While":[0],"recent":[1],"pre-training":[2,14],"tasks":[3],"on":[4,193],"2D":[5],"images":[6],"have":[7],"proven":[8],"very":[9],"successful":[10],"for":[11,15,28,134,142],"transfer":[12],"learning,":[13],"3D":[16,29,51,60],"data":[17,96,150],"remains":[18,35],"challenging.":[19],"In":[20,175],"this":[21,91],"work,":[22],"we":[23,177],"introduce":[24],"a":[25,63,83,95],"general":[26],"method":[27,181],"self-supervised":[30,70],"representation":[31],"learning":[32],"that":[33,77,90,112,127,179],"1)":[34],"agnostic":[36],"to":[37,154,169],"the":[38,47,75,143,155,160],"underlying":[39],"neural":[40,130],"network":[41,131],"architecture,":[42],"and":[43,89,199],"2)":[44],"specifically":[45],"leverages":[46],"geometric":[48,67,173],"nature":[49],"of":[50,66,108],"point":[52,136],"cloud":[53,137],"data.":[54],"The":[55],"proposed":[56,144],"task":[57,101],"softly":[58],"segments":[59],"points":[61],"into":[62],"discrete":[64,121],"number":[65],"partitions.":[68],"A":[69],"loss":[71],"is":[72],"formed":[73,158],"under":[74],"interpretation":[76],"these":[78],"soft":[79,156],"partitions":[80,157],"implicitly":[81,118],"parameterize":[82],"latent":[84],"Gaussian":[85],"Mixture":[86],"Model":[87],"(GMM),":[88],"generative":[92,122],"model":[93,123,197],"establishes":[94],"likelihood":[97,151],"function.":[98],"Our":[99],"pretext":[100,146],"can":[102,139],"therefore":[103],"be":[104,140],"viewed":[105],"in":[106,186,190],"terms":[107],"an":[109,117],"encoder-decoder":[110],"paradigm":[111],"squeezes":[113],"learned":[114,165],"representations":[115,166],"through":[116],"defined":[119],"parametric":[120],"bottleneck.":[124],"We":[125],"show":[126,178],"any":[128],"existing":[129],"architecture":[132],"designed":[133],"supervised":[135],"segmentation":[138,163],"repurposed":[141],"unsupervised":[145,161],"task.":[147],"By":[148],"maximizing":[149],"with":[152],"respect":[153],"by":[159],"point-wise":[162],"network,":[164],"are":[167],"encouraged":[168],"contain":[170],"compositionally":[171],"rich":[172],"information.":[174],"tests,":[176],"our":[180],"naturally":[182],"induces":[183],"semantic":[184,200],"separation":[185],"feature":[187],"space,":[188],"resulting":[189],"state-of-the-art":[191],"performance":[192],"downstream":[194],"applications":[195],"like":[196],"classification":[198],"segmentation.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}