{"id":"https://openalex.org/W4392903488","doi":"https://doi.org/10.1109/icassp48485.2024.10446195","title":"NERF-AD: Neural Radiance Field With Attention-Based Disentanglement For Talking Face Synthesis","display_name":"NERF-AD: Neural Radiance Field With Attention-Based Disentanglement For Talking Face Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903488","doi":"https://doi.org/10.1109/icassp48485.2024.10446195"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783771","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,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","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,Tianjin,China","College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,College of Intelligence and Computing,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, 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":2.8923,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93189908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3490","last_page":"3494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994000196456909,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9977999925613403,"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/computer-science","display_name":"Computer science","score":0.804375410079956},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6381707191467285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5552880167961121},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.537054181098938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49340763688087463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49042364954948425},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47989189624786377},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43819183111190796},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43638747930526733},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4352593421936035},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4186477065086365},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1371854543685913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804375410079956},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6381707191467285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5552880167961121},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.537054181098938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49340763688087463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49042364954948425},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47989189624786377},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43819183111190796},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43638747930526733},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4352593421936035},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4186477065086365},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1371854543685913},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7168884680","display_name":null,"funder_award_id":"62172294","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2133665775","https://openalex.org/W2186222003","https://openalex.org/W2418739498","https://openalex.org/W2807126412","https://openalex.org/W2883861033","https://openalex.org/W2962785568","https://openalex.org/W2962914239","https://openalex.org/W2963081548","https://openalex.org/W2996777077","https://openalex.org/W3081492798","https://openalex.org/W3093450153","https://openalex.org/W3101631197","https://openalex.org/W3105573053","https://openalex.org/W3109585842","https://openalex.org/W3186700381","https://openalex.org/W3197199219","https://openalex.org/W3207093815","https://openalex.org/W3211147706","https://openalex.org/W4214731463","https://openalex.org/W4226204502","https://openalex.org/W4288282320","https://openalex.org/W4295521014","https://openalex.org/W4312444931","https://openalex.org/W4323891935","https://openalex.org/W4386066799","https://openalex.org/W4387967971","https://openalex.org/W6640090968","https://openalex.org/W6735913928","https://openalex.org/W6765865358","https://openalex.org/W6803206414","https://openalex.org/W6811548253","https://openalex.org/W6840608358","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Talking":[0],"face":[1,105,125,185],"synthesis":[2,106],"driven":[3],"by":[4],"audio":[5,71,141,152],"is":[6,120,158],"one":[7],"of":[8,16,43,96,165],"the":[9,14,38,44,73,124,143,149,163],"current":[10],"research":[11,32],"hotspots":[12],"in":[13,34,84,181],"fields":[15],"multidimensional":[17],"signal":[18],"processing":[19],"and":[20,40,101,128,171,190],"multimedia.":[21],"Neural":[22],"Radiance":[23],"Field":[24],"(NeRF)":[25],"has":[26],"recently":[27],"been":[28],"brought":[29],"to":[30,36,72,77,122,161,199],"this":[31],"field":[33],"order":[35],"enhance":[37],"realism":[39],"3D":[41],"effect":[42],"generated":[45],"faces.":[46],"However,":[47],"most":[48],"existing":[49,85],"NeRF-based":[50],"methods":[51,61,86,180],"either":[52],"burden":[53],"NeRF":[54,97,109],"with":[55,110,151],"complex":[56],"learning":[57,98],"tasks":[58,99],"while":[59],"lacking":[60],"for":[62],"supervised":[63],"multimodal":[64],"feature":[65],"fusion,":[66],"or":[67],"cannot":[68],"precisely":[69,138],"map":[70],"facial":[74,132],"region":[75],"related":[76],"speech":[78],"movements.":[79],"These":[80],"reasons":[81],"ultimately":[82],"result":[83],"generating":[87,182],"inaccurate":[88],"lip":[89,191],"shapes.":[90],"This":[91],"paper":[92],"moves":[93],"a":[94,103],"portion":[95],"ahead":[100],"proposes":[102],"talking":[104,144,184],"method":[107],"via":[108],"attention-based":[111],"disentanglement":[112],"(NeRF-AD).":[113],"In":[114,154],"particular,":[115],"an":[116],"Attention-based":[117],"Disentanglement":[118],"module":[119],"introduced":[121],"disentangle":[123],"into":[126],"Audio-face":[127,150],"Identity-face":[129],"using":[130],"speech-related":[131],"action":[133],"unit":[134],"(AU)":[135],"information.":[136],"To":[137,193],"regulate":[139],"how":[140],"affects":[142],"face,":[145],"we":[146],"only":[147],"fuse":[148],"feature.":[153],"addition,":[155],"AU":[156],"information":[157],"also":[159],"utilized":[160],"supervise":[162],"fusion":[164],"these":[166],"two":[167],"modalities.":[168],"Extensive":[169],"qualitative":[170],"quantitative":[172],"experiments":[173],"demonstrate":[174],"that":[175],"our":[176],"NeRF-AD":[177],"outperforms":[178],"state-of-the-art":[179],"realistic":[183],"videos,":[186],"including":[187],"image":[188],"quality":[189],"synchronization.":[192],"view":[194],"video":[195],"results,":[196],"please":[197],"refer":[198],"https://xiaoxingliu02.github.io/NeRF-AD/.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-03-19T00:00:00"}
