{"id":"https://openalex.org/W4321020813","doi":"https://doi.org/10.1109/fg57933.2023.10042567","title":"LipNeRF: What is the right feature space to lip-sync a NeRF?","display_name":"LipNeRF: What is the right feature space to lip-sync a NeRF?","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4321020813","doi":"https://doi.org/10.1109/fg57933.2023.10042567"},"language":"en","primary_location":{"id":"doi:10.1109/fg57933.2023.10042567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5059880574","display_name":"Aggelina Chatziagapi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aggelina Chatziagapi","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008464830","display_name":"ShahRukh Athar","orcid":"https://orcid.org/0000-0002-8871-669X"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ShahRukh Athar","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050387442","display_name":"Abhinav Jain","orcid":"https://orcid.org/0000-0001-7993-169X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Jain","raw_affiliation_strings":["Amazon Prime Video"],"affiliations":[{"raw_affiliation_string":"Amazon Prime Video","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112428808","display_name":"Rohith MV","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohith MV","raw_affiliation_strings":["Amazon Prime Video"],"affiliations":[{"raw_affiliation_string":"Amazon Prime Video","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050133239","display_name":"Vimal Bhat","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vimal Bhat","raw_affiliation_strings":["Amazon Prime Video"],"affiliations":[{"raw_affiliation_string":"Amazon Prime Video","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076307452","display_name":"Dimitris Samaras","orcid":"https://orcid.org/0000-0002-1373-0294"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris Samaras","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059880574"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":4.3583,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95486671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11448","display_name":"Face recognition and analysis","score":0.996399998664856,"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":0.9937000274658203,"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":0.7608395218849182},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.7189527153968811},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6410000324249268},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5743418335914612},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5659037232398987},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5529972910881042},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.527367889881134},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4629005193710327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4471745491027832},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44379132986068726},{"id":"https://openalex.org/keywords/radiance","display_name":"Radiance","score":0.4344191253185272},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42835646867752075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3732105493545532},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.15541425347328186},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10297033190727234},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0881747305393219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608395218849182},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.7189527153968811},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6410000324249268},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5743418335914612},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5659037232398987},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5529972910881042},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.527367889881134},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4629005193710327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4471745491027832},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44379132986068726},{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.4344191253185272},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42835646867752075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3732105493545532},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.15541425347328186},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10297033190727234},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0881747305393219},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg57933.2023.10042567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg57933.2023.10042567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W71477782","https://openalex.org/W1569907127","https://openalex.org/W1922655562","https://openalex.org/W2017107803","https://openalex.org/W2070726616","https://openalex.org/W2107037917","https://openalex.org/W2109606373","https://openalex.org/W2120067677","https://openalex.org/W2133665775","https://openalex.org/W2147885303","https://openalex.org/W2237250383","https://openalex.org/W2289286917","https://openalex.org/W2295661697","https://openalex.org/W2604379605","https://openalex.org/W2607170299","https://openalex.org/W2738406145","https://openalex.org/W2803705807","https://openalex.org/W2806833697","https://openalex.org/W2807725536","https://openalex.org/W2914217321","https://openalex.org/W2942074357","https://openalex.org/W2944294033","https://openalex.org/W2962785568","https://openalex.org/W2963290645","https://openalex.org/W2963767194","https://openalex.org/W2969222682","https://openalex.org/W2982763192","https://openalex.org/W3019952993","https://openalex.org/W3034521057","https://openalex.org/W3034577585","https://openalex.org/W3034600949","https://openalex.org/W3036235590","https://openalex.org/W3043547428","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3119388918","https://openalex.org/W3128081663","https://openalex.org/W3129086450","https://openalex.org/W3143336910","https://openalex.org/W3175779516","https://openalex.org/W3177583232","https://openalex.org/W3182714435","https://openalex.org/W3186090335","https://openalex.org/W3203570626","https://openalex.org/W3211147706","https://openalex.org/W4214731463","https://openalex.org/W4226204502","https://openalex.org/W4287552895","https://openalex.org/W4312233178","https://openalex.org/W4312959196","https://openalex.org/W4321033021","https://openalex.org/W6765657114","https://openalex.org/W6786663908","https://openalex.org/W6799610062","https://openalex.org/W6811548253"],"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/W2005276308","https://openalex.org/W1970182911","https://openalex.org/W2349443037","https://openalex.org/W1994657804","https://openalex.org/W2347721387"],"abstract_inverted_index":{"Synthesizing":[0],"high-fidelity":[1],"talking":[2],"head":[3,49],"videos":[4,171],"of":[5,31,40,87,109,118,127,131,172],"an":[6],"arbitrary":[7],"identity,":[8],"lip-synced":[9],"to":[10,36,47],"a":[11,16,25,28,38,88,97,128,144,158],"target":[12],"speech":[13],"segment,":[14],"is":[15,121],"challenging":[17,176],"problem.":[18],"Recent":[19],"GAN-based":[20,110],"methods":[21,111],"succeed":[22],"by":[23],"training":[24],"model":[26,60],"on":[27,83,123],"large":[29],"amount":[30],"videos,":[32],"allowing":[33],"the":[34,53,61,102,105,113,124,132,140,148,152,165],"generator":[35],"learn":[37],"variety":[39],"audio-lip":[41],"representations.":[42],"However,":[43],"they":[44,80],"are":[45,70,81],"unable":[46],"handle":[48],"pose":[50],"changes.":[51],"On":[52],"other":[54],"hand,":[55],"Neural":[56],"Radiance":[57],"Fields":[58],"(NeRFs)":[59],"3D":[62,115],"face":[63,116],"geometry":[64],"more":[65],"accurately.":[66],"Current":[67],"audio-conditioned":[68],"NeRFs":[69],"not":[71],"as":[72,77],"good":[73],"in":[74,161,169],"lip":[75,107,149],"synchronization":[76,108],"GANs,":[78],"since":[79],"trained":[82],"limited":[84],"video":[85],"data":[86],"single":[89],"identity.":[90],"In":[91],"this":[92],"work,":[93],"we":[94],"propose":[95],"LipNeRF,":[96],"lip-syncing":[98],"NeRF":[99],"that":[100,139],"bridges":[101],"gap":[103],"between":[104],"accurate":[106,114],"and":[112,179],"modeling":[117],"NeRFs.":[119],"LipNeRF":[120,156],"conditioned":[122],"expression":[125,141,180],"space":[126,142],"3DMM,":[129],"instead":[130],"audio":[133,153],"feature":[134,154],"space.":[135,155],"We":[136],"experimentally":[137],"demonstrate":[138],"gives":[143],"better":[145],"representation":[146],"for":[147],"shape":[150],"than":[151],"shows":[157],"significant":[159],"improvement":[160],"lip-sync":[162],"quality":[163],"over":[164],"current":[166],"state-of-the-art,":[167],"especially":[168],"high-definition":[170],"cinematic":[173],"content,":[174],"with":[175],"pose,":[177],"illumination":[178],"variations.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}
