{"id":"https://openalex.org/W4401386940","doi":"https://doi.org/10.1109/tcsvt.2024.3439737","title":"OV-NeRF: Open-Vocabulary Neural Radiance Fields With Vision and Language Foundation Models for 3D Semantic Understanding","display_name":"OV-NeRF: Open-Vocabulary Neural Radiance Fields With Vision and Language Foundation Models for 3D Semantic Understanding","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401386940","doi":"https://doi.org/10.1109/tcsvt.2024.3439737"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3439737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439737","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","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/A5047649165","display_name":"Guibiao Liao","orcid":"https://orcid.org/0000-0002-5714-1926"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guibiao Liao","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078078782","display_name":"Kaichen Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaichen Zhou","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","Department of Computer Science, University of Oxford, Oxfordshire, England"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]},{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxfordshire, England","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090395727","display_name":"Zhenyu Bao","orcid":"https://orcid.org/0000-0003-1368-9364"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Bao","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004007577","display_name":"Kanglin Liu","orcid":"https://orcid.org/0000-0002-6293-5464"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Kanglin Liu","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qing Li","orcid":"https://orcid.org/0000-0002-7816-9733"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]},{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047649165"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":4.6548,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95955366,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"34","issue":"12","first_page":"12923","last_page":"12936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9702000021934509,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9702000021934509,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9587000012397766,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9535999894142151,"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/radiance","display_name":"Radiance","score":0.7366527915000916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6895073652267456},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6042267084121704},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5741392374038696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5437804460525513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4609459340572357},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4205203652381897},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4164116680622101},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.1774648129940033},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16525894403457642},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14210522174835205}],"concepts":[{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.7366527915000916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895073652267456},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6042267084121704},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5741392374038696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437804460525513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4609459340572357},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4205203652381897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4164116680622101},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.1774648129940033},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16525894403457642},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14210522174835205},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3439737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439737","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1374776911","display_name":null,"funder_award_id":"62101290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1537954158","display_name":null,"funder_award_id":"PCL2023A10-1","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2000215628","https://openalex.org/W2594519801","https://openalex.org/W3008115128","https://openalex.org/W3010797203","https://openalex.org/W3109585842","https://openalex.org/W3159481202","https://openalex.org/W3162105812","https://openalex.org/W3176368002","https://openalex.org/W3203570626","https://openalex.org/W3210613940","https://openalex.org/W3215769467","https://openalex.org/W4214731463","https://openalex.org/W4221151978","https://openalex.org/W4252201060","https://openalex.org/W4293704575","https://openalex.org/W4312234520","https://openalex.org/W4312280100","https://openalex.org/W4312563428","https://openalex.org/W4312960937","https://openalex.org/W4317987768","https://openalex.org/W4321488276","https://openalex.org/W4321512591","https://openalex.org/W4361989318","https://openalex.org/W4376454263","https://openalex.org/W4383108296","https://openalex.org/W4385413681","https://openalex.org/W4385431115","https://openalex.org/W4385834285","https://openalex.org/W4386065512","https://openalex.org/W4386075561","https://openalex.org/W4386076397","https://openalex.org/W4390872696","https://openalex.org/W4390872744","https://openalex.org/W4390873343","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4394586034","https://openalex.org/W6764040762","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6811433417","https://openalex.org/W6839087412","https://openalex.org/W6843201930","https://openalex.org/W6845830698","https://openalex.org/W6846835116","https://openalex.org/W6852629184","https://openalex.org/W6852907144","https://openalex.org/W6853702739","https://openalex.org/W6855205047","https://openalex.org/W6856473036","https://openalex.org/W6857416157"],"related_works":["https://openalex.org/W2896728493","https://openalex.org/W2392142157","https://openalex.org/W2043512367","https://openalex.org/W4321518006","https://openalex.org/W2331836163","https://openalex.org/W1994657804","https://openalex.org/W2005276308","https://openalex.org/W1970182911","https://openalex.org/W2024462231","https://openalex.org/W2347721387"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,19,25,76,121,202],"Neural":[3],"Radiance":[4],"Fields":[5],"(NeRFs)":[6],"has":[7,33],"provided":[8,62],"a":[9,35,137,199],"potent":[10],"representation":[11],"for":[12,50,173],"encapsulating":[13],"the":[14,23,74,96,118,132,144,154,162,168],"geometric":[15],"and":[16,59,79,91,181,204,211],"appearance":[17],"characteristics":[18],"3D":[20,29,163],"scenes.":[21],"Enhancing":[22],"capabilities":[24],"NeRFs":[26],"in":[27,206],"open-vocabulary":[28],"semantic":[30,51,85,127,170,174,184],"perception":[31],"tasks":[32],"been":[34],"recent":[36],"focus.":[37],"However,":[38],"current":[39,195],"methods":[40],"that":[41],"extract":[42],"semantics":[43,61,120,157,165],"directly":[44],"from":[45,95,112,131,158,167],"Contrastive":[46],"Language-Image":[47],"Pretraining":[48],"(CLIP)":[49],"field":[52,86,128,171,175],"learning":[53,87],"encounter":[54],"difficulties":[55],"due":[56],"to":[57,83,116,142,178],"noisy":[58,119],"view-inconsistent":[60,148],"by":[63,106,147],"CLIP.":[64],"To":[65],"tackle":[66],"these":[67],"limitations,":[68],"we":[69,99,135],"propose":[70,136],"OV-NeRF,":[71],"which":[72],"exploits":[73],"potential":[75],"pre-trained":[77],"vision":[78],"language":[80],"foundation":[81],"models":[82],"enhance":[84,182],"through":[88],"proposed":[89],"single-view":[90,97],"cross-view":[92,133],"strategies.":[93],"First,":[94],"perspective,":[98,134],"introduce":[100],"Region":[101],"Semantic":[102],"Ranking":[103],"(RSR)":[104],"regularization":[105],"leveraging":[107],"2D":[108,155],"mask":[109],"proposals":[110],"derived":[111],"Segment":[113],"Anything":[114],"(SAM)":[115],"rectify":[117],"each":[122],"training":[123],"view,":[124],"facilitating":[125],"accurate":[126],"learning.":[129],"Second,":[130],"Cross-view":[138],"Self-enhancement":[139],"(CSE)":[140],"strategy":[141],"address":[143],"challenge":[145],"raised":[146],"semantics.":[149],"Rather":[150],"than":[151],"invariably":[152],"utilizing":[153],"inconsistent":[156],"CLIP,":[159],"CSE":[160],"leverages":[161],"consistent":[164,218],"generated":[166],"well-trained":[169],"itself":[172],"training,":[176],"aiming":[177],"reduce":[179],"ambiguity":[180],"overall":[183],"consistency":[185],"across":[186,221],"different":[187],"views.":[188],"Extensive":[189],"experiments":[190],"validate":[191],"our":[192,215],"OV-NeRF":[193],"outperforms":[194],"state-of-the-art":[196],"methods,":[197],"achieving":[198],"significant":[200],"improvement":[201],"20.31%":[203],"18.42%":[205],"mIoU":[207],"metric":[208],"on":[209],"Replica":[210],"ScanNet,":[212],"respectively.":[213],"Furthermore,":[214],"approach":[216],"exhibits":[217],"superior":[219],"results":[220],"various":[222],"CLIP":[223],"configurations,":[224],"further":[225],"verifying":[226],"its":[227],"robustness.":[228],"Codes":[229],"are":[230],"available":[231],"at:":[232],"<uri":[233],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[234],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/pcl3dv/OV-NeRF</uri>.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}