{"id":"https://openalex.org/W4414811210","doi":"https://doi.org/10.1145/3757377.3763854","title":"Audio Driven Real-Time Facial Animation for Social Telepresence","display_name":"Audio Driven Real-Time Facial Animation for Social Telepresence","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W4414811210","doi":"https://doi.org/10.1145/3757377.3763854"},"language":"en","primary_location":{"id":"doi:10.1145/3757377.3763854","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.01176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiye Lee","orcid":"https://orcid.org/0000-0001-8948-0589"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiye Lee","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8948-0589","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenghui Li","orcid":"https://orcid.org/0009-0003-7055-5757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenghui Li","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0003-7055-5757","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linh Tran","orcid":"https://orcid.org/0000-0002-8715-1076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linh Tran","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-8715-1076","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shih-En Wei","orcid":"https://orcid.org/0000-0002-0092-3441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shih-En Wei","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-0092-3441","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082178717","display_name":"Jason Saragih","orcid":"https://orcid.org/0000-0001-6218-5029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Saragih","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0001-6218-5029","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108760515","display_name":"Alexander Richard","orcid":"https://orcid.org/0009-0000-5173-6438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Richard","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0000-5173-6438","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036077761","display_name":"Hanbyul Joo","orcid":"https://orcid.org/0000-0002-6666-7460"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbyul Joo","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6666-7460","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shaojie Bai","orcid":"https://orcid.org/0009-0001-7969-9429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojie Bai","raw_affiliation_strings":["Codec Avatars Lab, Meta, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0001-7969-9429","affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta, Pittsburgh, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29095599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9966999888420105,"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":0.9966999888420105,"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/T12290","display_name":"Human Motion and Animation","score":0.9405999779701233,"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/computer-facial-animation","display_name":"Computer facial animation","score":0.5715000033378601},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.53329998254776},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.49129998683929443},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4440000057220459},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.4348999857902527},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8457000255584717},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5715000033378601},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.44760000705718994},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38960000872612},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27959999442100525},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3757377.3763854","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757377.3763854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.01176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01176","pdf_url":"https://arxiv.org/pdf/2510.01176","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.01176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.01176","pdf_url":"https://arxiv.org/pdf/2510.01176","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4414811210.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,109,177],"present":[1],"an":[2,29,88],"audio-driven":[3],"real-time":[4,74],"system":[5],"for":[6,16,22,69,118],"animating":[7],"photorealistic":[8,49],"3D":[9,50],"facial":[10,38,51,66,161],"avatars":[11],"with":[12,148],"minimal":[13],"latency,":[14],"designed":[15],"social":[17],"interactions":[18],"in":[19,41,115,160],"virtual":[20],"reality":[21],"anyone.":[23],"Central":[24],"to":[25,135,171],"our":[26,132,179],"approach":[27,180],"is":[28],"encoder":[30],"model":[31],"that":[32,91,101],"transforms":[33],"audio":[34,121],"signals":[35,122],"into":[36,105],"latent":[37],"expression":[39],"sequences":[40],"real":[42],"time,":[43],"which":[44],"are":[45],"then":[46],"decoded":[47],"as":[48,142,190],"avatars.":[52],"Leveraging":[53],"the":[54,62],"generative":[55],"capabilities":[56],"of":[57,65,131],"diffusion":[58],"models,":[59],"we":[60],"capture":[61],"rich":[63],"spectrum":[64],"expressions":[67],"necessary":[68],"natural":[70],"communication":[71],"while":[72,124],"achieving":[73,169],"performance":[75],"(<15ms":[76],"GPU":[77],"time).":[78],"Our":[79],"novel":[80],"architecture":[81],"minimizes":[82],"latency":[83],"through":[84,181],"two":[85],"key":[86],"innovations:":[87],"online":[89],"transformer":[90],"eliminates":[92],"dependency":[93],"on":[94,152],"future":[95],"inputs":[96],"and":[97,145,185],"a":[98,106],"distillation":[99],"pipeline":[100],"accelerates":[102],"iterative":[103],"denoising":[104],"single":[107],"step.":[108],"further":[110],"address":[111],"critical":[112],"design":[113],"challenges":[114],"live":[116,182],"scenarios":[117,188],"processing":[119],"continuous":[120],"frame-by-frame":[123],"maintaining":[125],"consistent":[126],"animation":[127,162],"quality.":[128],"The":[129],"versatility":[130],"framework":[133],"extends":[134],"multimodal":[136,146],"applications,":[137],"including":[138],"semantic":[139],"modalities":[140],"such":[141,189],"emotion":[143],"conditions":[144],"sensors":[147],"head-mounted":[149],"eye":[150],"cameras":[151],"VR":[153,183],"headsets.":[154],"Experimental":[155],"results":[156],"demonstrate":[157],"significant":[158],"improvements":[159],"accuracy":[163],"over":[164],"existing":[165],"offline":[166],"state-of-the-art":[167],"baselines,":[168],"100":[170],"1000":[172],"\u00d7":[173],"faster":[174],"inference":[175],"speed.":[176],"validate":[178],"demonstrations":[184],"across":[186],"various":[187],"multilingual":[191],"speeches.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}