{"id":"https://openalex.org/W4408352166","doi":"https://doi.org/10.1109/icassp49660.2025.10889538","title":"NeRF-3DTalker: Neural Radiance Field with 3D Prior Aided Audio Disentanglement for Talking Head Synthesis","display_name":"NeRF-3DTalker: Neural Radiance Field with 3D Prior Aided Audio Disentanglement for Talking Head Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352166","doi":"https://doi.org/10.1109/icassp49660.2025.10889538"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078008447","display_name":"Xiaoxing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxing Liu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055459279","display_name":"Zhilei Liu","orcid":"https://orcid.org/0000-0003-1447-6256"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilei Liu","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100786077","display_name":"Chongke Bi","orcid":"https://orcid.org/0000-0002-4324-8028"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongke Bi","raw_affiliation_strings":["Tianjin University,College of Intelligence and Computing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":16.9371,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.99124517,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9233999848365784,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T13382","display_name":"Robotics and Automated Systems","score":0.9233999848365784,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/radiance","display_name":"Radiance","score":0.8296852111816406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833245754241943},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6640224456787109},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5033742785453796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3773195147514343},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3400750160217285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.333354651927948},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3277609646320343},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.08166259527206421},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07602065801620483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06780433654785156}],"concepts":[{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.8296852111816406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833245754241943},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6640224456787109},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5033742785453796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3773195147514343},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3400750160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.333354651927948},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3277609646320343},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.08166259527206421},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07602065801620483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06780433654785156},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"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":29,"referenced_works":["https://openalex.org/W1628791547","https://openalex.org/W2133665775","https://openalex.org/W2752796333","https://openalex.org/W2754447548","https://openalex.org/W2796822548","https://openalex.org/W2807126412","https://openalex.org/W2883861033","https://openalex.org/W2962785568","https://openalex.org/W2962914239","https://openalex.org/W2963081548","https://openalex.org/W3034192160","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3109585842","https://openalex.org/W3174763799","https://openalex.org/W3176179930","https://openalex.org/W4200174933","https://openalex.org/W4312253380","https://openalex.org/W4312990833","https://openalex.org/W4375868848","https://openalex.org/W4386072021","https://openalex.org/W4386076250","https://openalex.org/W4392903488","https://openalex.org/W4394597549","https://openalex.org/W4399740326","https://openalex.org/W4402726971","https://openalex.org/W4411245064","https://openalex.org/W6849049266"],"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/W2024462231","https://openalex.org/W2005276308","https://openalex.org/W1994657804","https://openalex.org/W1970182911","https://openalex.org/W2347721387"],"abstract_inverted_index":{"Talking":[0,109],"head":[1,9,71,224],"synthesis":[2,72],"is":[3,73,140],"to":[4,18,56,121,142,152,160,164],"synthesize":[5,122],"a":[6,132,184],"lip-synchronized":[7],"talking":[8,27,59,70,91,124,223],"video":[10],"using":[11],"audio.":[12],"Recently,":[13],"the":[14,20,31,47,74,89,114,144,166,173,178,191,195],"capability":[15],"of":[16,25,33,49,88],"NeRF":[17,38],"enhance":[19],"realism":[21],"and":[22,79,157,201,208,230],"texture":[23],"details":[24],"synthesized":[26],"heads":[28,60,125],"has":[29,212],"attracted":[30],"attention":[32],"researchers.":[34],"However,":[35],"most":[36],"current":[37,68],"methods":[39,53],"based":[40],"on":[41],"audio":[42,145],"are":[43,54,170],"exclusively":[44],"concerned":[45],"with":[46,102,126],"rendering":[48],"frontal":[50],"faces.":[51],"These":[52],"unable":[55],"generate":[57],"clear":[58,123],"in":[61,67,76,85,177,194,220],"novel":[62],"views.":[63,128],"Another":[64],"prevalent":[65],"challenge":[66],"3D":[69,103,118,133,153],"difficulty":[75],"aligning":[77],"acoustic":[78],"visual":[80],"spaces,":[81],"which":[82,139],"often":[83],"results":[84],"suboptimal":[86],"lip-syncing":[87],"generated":[90,167,196],"heads.":[92],"To":[93],"address":[94],"these":[95],"issues,":[96],"we":[97,130,181],"propose":[98,131],"Neural":[99],"Radiance":[100],"Field":[101],"Prior":[104,134],"Aided":[105,135],"Audio":[106,136],"Disentanglement":[107,137],"for":[108],"Head":[110],"Synthesis":[111],"(NeRF-3DTalker).":[112],"Specifically,":[113],"proposed":[115],"method":[116,189],"employs":[117],"prior":[119],"information":[120],"free":[127],"Additionally,":[129],"module,":[138],"designed":[141],"disentangle":[143],"into":[146],"two":[147],"distinct":[148],"categories:":[149],"features":[150,158],"related":[151,159],"awarded":[154],"speech":[155],"movements":[156],"speaking":[161],"style.":[162],"Moreover,":[163],"reposition":[165],"frames":[168,197],"that":[169,215],"distant":[171],"from":[172,198],"speaker\u2019s":[174],"motion":[175],"space":[176],"real":[179],"space,":[180],"have":[182],"devised":[183],"local-global":[185],"Standardized":[186],"Space.":[187],"This":[188],"normalizes":[190],"irregular":[192],"positions":[193],"both":[199],"global":[200],"local":[202],"semantic":[203],"perspectives.":[204],"Through":[205],"comprehensive":[206],"qualitative":[207],"quantitative":[209],"experiments,":[210],"it":[211],"been":[213],"demonstrated":[214],"our":[216],"NeRF3DTalker":[217],"outperforms":[218],"state-of-the-art":[219],"synthesizing":[221],"realistic":[222],"videos,":[225],"exhibiting":[226],"superior":[227],"image":[228],"quality":[229],"lip":[231],"synchronization.":[232],"Project":[233],"page:":[234],"https://nerf-3dtalker.github.io/NeRF-3Dtalker/.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}