{"id":"https://openalex.org/W4390873153","doi":"https://doi.org/10.1109/iccv51070.2023.02131","title":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","display_name":"NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390873153","doi":"https://doi.org/10.1109/iccv51070.2023.02131"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.02131","doi":"https://doi.org/10.1109/iccv51070.2023.02131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.02131","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.14620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083914796","display_name":"Chenfeng Xu","orcid":"https://orcid.org/0000-0002-4941-6985","observed_orcids":["https://orcid.org/0000-0002-4941-6985"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenfeng Xu","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120863457","display_name":"Bichen Wu","orcid":"https://orcid.org/0000-0002-2649-5561","observed_orcids":["https://orcid.org/0000-0002-2649-5561"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bichen Wu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586274","display_name":"Ji Hou","orcid":"https://orcid.org/0000-0002-5244-8953","observed_orcids":["https://orcid.org/0000-0002-5244-8953"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Hou","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113536035","display_name":"Sam S. Tsai","orcid":"https://orcid.org/0000-0002-7220-9108","observed_orcids":["https://orcid.org/0000-0002-7220-9108"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Tsai","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101961149","display_name":"Ruilong Li","orcid":"https://orcid.org/0000-0003-4536-3932","observed_orcids":["https://orcid.org/0000-0003-4536-3932"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruilong Li","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677918","display_name":"Jialiang Wang","orcid":"https://orcid.org/0000-0002-2776-5703","observed_orcids":["https://orcid.org/0000-0002-2776-5703","https://orcid.org/0009-0002-7938-0028","https://orcid.org/0009-0003-2397-4828"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialiang Wang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770873","display_name":"Wei Zhan","orcid":"https://orcid.org/0000-0002-1474-1200","observed_orcids":["https://orcid.org/0000-0002-1474-1200"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhan","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108752809","display_name":"Zijian He","orcid":"https://orcid.org/0009-0003-8731-6090","observed_orcids":["https://orcid.org/0009-0003-8731-6090","https://orcid.org/0009-0003-1845-2195"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian He","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048668303","display_name":"P\u00e9ter Vajda","orcid":"https://orcid.org/0000-0002-2031-4678","observed_orcids":["https://orcid.org/0000-0002-2031-4678"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Vajda","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501","observed_orcids":["https://orcid.org/0000-0003-3868-8501"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639","observed_orcids":["https://orcid.org/0000-0003-0206-6639"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7419,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.98468909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"23263","last_page":"23273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.798799991607666,"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":0.798799991607666,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.15629999339580536,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.016200000420212746,"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/neural-radiance-fields","display_name":"neural radiance fields","score":0.6420000195503235},{"id":"https://openalex.org/keywords/volumetric-representation","display_name":"volumetric representation","score":0.7049999833106995},{"id":"https://openalex.org/keywords/3d-object-detection","display_name":"3D object detection","score":0.8989999890327454},{"id":"https://openalex.org/keywords/multi-view-detection","display_name":"multi-view detection","score":0.7020000219345093},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.5879999995231628},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"view synthesis","score":0.6700000166893005},{"id":"https://openalex.org/keywords/depth-estimation","display_name":"depth estimation","score":0.9860000014305115},{"id":"https://openalex.org/keywords/scannet","display_name":"ScanNet","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419854402542114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6991150379180908},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6537029147148132},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6042500138282776},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43644917011260986},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42225056886672974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27179405093193054},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51070.2023.02131","doi":"https://doi.org/10.1109/iccv51070.2023.02131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.02131","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.14620","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.14620","pdf_url":"https://arxiv.org/pdf/2307.14620","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.14620","doi":"https://doi.org/10.48550/arxiv.2307.14620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.14620","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.14620","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.14620","pdf_url":"https://arxiv.org/pdf/2307.14620","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390873153.pdf","grobid_xml":"https://content.openalex.org/works/W4390873153.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W2074254947","https://openalex.org/W2122572959","https://openalex.org/W2132947399","https://openalex.org/W2160014001","https://openalex.org/W2471962767","https://openalex.org/W2565639579","https://openalex.org/W2769205412","https://openalex.org/W2769312834","https://openalex.org/W2904332125","https://openalex.org/W2939384298","https://openalex.org/W2955639361","https://openalex.org/W2962759414","https://openalex.org/W2963150697","https://openalex.org/W3003352491","https://openalex.org/W3014777739","https://openalex.org/W3034600477","https://openalex.org/W3034626012","https://openalex.org/W3096754345","https://openalex.org/W3136327392","https://openalex.org/W3136656704","https://openalex.org/W3166573884","https://openalex.org/W3171032126","https://openalex.org/W3172610252","https://openalex.org/W3173522942","https://openalex.org/W3174960126","https://openalex.org/W3176368002","https://openalex.org/W3177292376","https://openalex.org/W3186630079","https://openalex.org/W3202804820","https://openalex.org/W3203257492","https://openalex.org/W3204859697","https://openalex.org/W3208757648","https://openalex.org/W3210613940","https://openalex.org/W3215207332","https://openalex.org/W3215270085","https://openalex.org/W4200150166","https://openalex.org/W4206760982","https://openalex.org/W4235111023","https://openalex.org/W4293167273","https://openalex.org/W4303443326","https://openalex.org/W4310443815","https://openalex.org/W4312433568","https://openalex.org/W4312433790","https://openalex.org/W4312539440","https://openalex.org/W4312679369","https://openalex.org/W4312706422","https://openalex.org/W4321512561","https://openalex.org/W4386075506","https://openalex.org/W4386075853","https://openalex.org/W6803096584","https://openalex.org/W6803754133","https://openalex.org/W6845491643","https://openalex.org/W6846095257","https://openalex.org/W7133205496"],"related_works":["https://openalex.org/W4416252143","https://openalex.org/W4413157838","https://openalex.org/W4415795190","https://openalex.org/W7171472716","https://openalex.org/W4386075506","https://openalex.org/W4406859963","https://openalex.org/W4411472313","https://openalex.org/W4409560874","https://openalex.org/W4415233561","https://openalex.org/W4390872943"],"abstract_inverted_index":{"We":[0,119],"present":[1],"NeRF-Det,":[2],"a":[3,83,131],"novel":[4,31],"method":[5,29,103],"for":[6,99,146],"indoor":[7,18],"3D":[8,19,42,46,100],"detection":[9,20,47,78,93],"with":[10,57],"posed":[11],"RGB":[12],"images":[13],"as":[14],"input.":[15],"Unlike":[16],"existing":[17],"methods":[21],"that":[22],"struggle":[23],"to":[24,39,50,67,92,123,140,143],"model":[25],"scene":[26],"geometry,":[27,43],"our":[28,134],"makes":[30],"use":[32],"of":[33,60,71,90,133],"NeRF":[34,80,91],"in":[35],"an":[36,87],"end-to-end":[37],"manner":[38],"explicitly":[40],"estimate":[41],"thereby":[44],"improving":[45],"performance.":[48],"Specifically,":[49],"avoid":[51],"the":[52,69,77,113],"significant":[53],"extra":[54],"latency":[55],"associated":[56],"per-scene":[58,157],"optimization":[59],"NeRF,":[61],"we":[62,74],"introduce":[63],"sufficient":[64],"geometry":[65],"priors":[66],"enhance":[68],"generalizability":[70],"NeRF-MLP.":[72],"Furthermore,":[73],"subtly":[75],"connect":[76],"and":[79,94,109,115,151],"branches":[81],"through":[82],"shared":[84],"MLP,":[85],"enabling":[86],"efficient":[88],"adaptation":[89],"yielding":[95],"geometry-aware":[96],"volumetric":[97],"representations":[98],"detection.":[101],"Our":[102],"outperforms":[104],"state-of-the-arts":[105],"by":[106],"3.9":[107],"mAP":[108,111],"3.1":[110],"on":[112,126],"ScanNet":[114],"ARKITScenes":[116],"benchmarks,":[117],"respectively.":[118],"provide":[120],"extensive":[121],"analysis":[122],"shed":[124],"light":[125],"how":[127],"NeRF-Det":[128,137],"works.":[129],"As":[130],"result":[132],"joint-training":[135],"design,":[136],"is":[138,160],"able":[139],"generalize":[141],"well":[142],"unseen":[144],"scenes":[145],"object":[147],"detection,":[148],"view":[149],"synthesis,":[150],"depth":[152],"estimation":[153],"tasks":[154],"without":[155],"requiring":[156],"optimization.":[158],"Code":[159],"available":[161],"at":[162],"https://github.com/facebookresearch/NeRF-Det.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-01-16T00:00:00"}