{"id":"https://openalex.org/W4408222799","doi":"https://doi.org/10.1109/tvcg.2025.3549168","title":"VASA-Rig: Audio-Driven 3D Facial Animation with \u2018Live\u2019 Mood Dynamics in Virtual Reality","display_name":"VASA-Rig: Audio-Driven 3D Facial Animation with \u2018Live\u2019 Mood Dynamics in Virtual Reality","publication_year":2025,"publication_date":"2025-03-07","ids":{"openalex":"https://openalex.org/W4408222799","doi":"https://doi.org/10.1109/tvcg.2025.3549168","pmid":"https://pubmed.ncbi.nlm.nih.gov/40053639"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3549168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3549168","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5043835037","display_name":"Ye Pan","orcid":"https://orcid.org/0000-0002-1447-6806"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Pan","raw_affiliation_strings":["Shanghai Jiao Tong University (SJTU), China"],"raw_orcid":"https://orcid.org/0000-0002-1447-6806","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University (SJTU), China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang Liu","orcid":"https://orcid.org/0009-0001-1379-2583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["SJTU, China"],"raw_orcid":"https://orcid.org/0009-0001-1379-2583","affiliations":[{"raw_affiliation_string":"SJTU, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077900121","display_name":"Sicheng Xu","orcid":"https://orcid.org/0000-0002-7903-3934"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Xu","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":"https://orcid.org/0000-0002-7903-3934","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012914294","display_name":"Shuai Tan","orcid":"https://orcid.org/0000-0003-3322-5161"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Tan","raw_affiliation_strings":["SJTU, China","Shanghai Jiao Tong University (SJTU), China"],"raw_orcid":"https://orcid.org/0000-0003-3322-5161","affiliations":[{"raw_affiliation_string":"SJTU, China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University (SJTU), China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076804411","display_name":"Jiaolong Yang","orcid":"https://orcid.org/0000-0002-7314-6567"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaolong Yang","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":"https://orcid.org/0000-0002-7314-6567","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8048,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89570437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"31","issue":"5","first_page":"2416","last_page":"2425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9368000030517578,"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":0.9368000030517578,"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":0.7628316879272461},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.67936110496521},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.659747302532196},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.629208505153656},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5844810009002686},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5753722786903381},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5467898845672607},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4266703426837921},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41944774985313416},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38116514682769775},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34070879220962524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3289638161659241},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1307424008846283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628316879272461},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.67936110496521},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.659747302532196},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.629208505153656},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5844810009002686},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5753722786903381},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5467898845672607},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4266703426837921},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41944774985313416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38116514682769775},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34070879220962524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3289638161659241},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1307424008846283},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2025.3549168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3549168","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:40053639","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40053639","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G10871201","display_name":null,"funder_award_id":"62472285","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":44,"referenced_works":["https://openalex.org/W1990883837","https://openalex.org/W2039239232","https://openalex.org/W2154961933","https://openalex.org/W2468212864","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2806833697","https://openalex.org/W2944294033","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W3081192838","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3154411171","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3212516020","https://openalex.org/W4200630629","https://openalex.org/W4281730245","https://openalex.org/W4312388283","https://openalex.org/W4321488265","https://openalex.org/W4380994134","https://openalex.org/W4386076250","https://openalex.org/W4388157164","https://openalex.org/W4390872334","https://openalex.org/W4390872428","https://openalex.org/W4390872742","https://openalex.org/W4390874567","https://openalex.org/W4391072501","https://openalex.org/W4392405761","https://openalex.org/W4393148434","https://openalex.org/W4393154048","https://openalex.org/W4394825433","https://openalex.org/W4400818936","https://openalex.org/W4402727135","https://openalex.org/W4403081627","https://openalex.org/W4403780536","https://openalex.org/W6780218876","https://openalex.org/W6786375611","https://openalex.org/W6859110512","https://openalex.org/W6860836835","https://openalex.org/W6864518445","https://openalex.org/W6875029971","https://openalex.org/W6907631384"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Audio-driven":[0],"3D":[1,47],"facial":[2,64,92],"animation":[3],"is":[4],"crucial":[5],"for":[6,116],"enhancing":[7],"the":[8,59,83,88],"metaverse's":[9],"realism,":[10],"immersion,":[11],"and":[12,23,41,66,81,138],"interactivity.":[13],"While":[14],"most":[15],"existing":[16,130],"methods":[17,132],"focus":[18],"on":[19],"generating":[20],"highly":[21],"realistic":[22],"lively":[24],"2D":[25,32,91],"talking":[26,78],"head":[27,67],"videos":[28],"by":[29],"leveraging":[30],"extensive":[31],"video":[33],"datasets":[34],"these":[35],"approaches":[36],"work":[37],"in":[38,58,104,133],"pixel":[39],"space":[40],"are":[42],"not":[43],"easily":[44],"adaptable":[45],"to":[46],"environments.":[48],"We":[49],"present":[50],"VASA-Rig,":[51],"which":[52,86],"has":[53],"achieved":[54],"a":[55,73],"significant":[56],"advancement":[57],"realism":[60,137],"of":[61,90,135],"lip-audio":[62],"synchronization,":[63],"dynamics,":[65],"movements.":[68],"In":[69],"particular,":[70],"we":[71],"introduce":[72],"novel":[74],"rig":[75,101,110],"parameter-based":[76],"emotional":[77],"face":[79],"dataset":[80],"propose":[82],"Latents2Rig":[84],"model,":[85],"facilitates":[87],"transformation":[89],"animations":[93],"into":[94,118],"3D.":[95],"Unlike":[96],"mesh-based":[97],"models,":[98],"VASA-Rig":[99],"outputs":[100],"parameters,":[102,111],"instantiated":[103],"this":[105],"paper":[106],"as":[107],"174":[108],"Metahuman":[109],"making":[112],"it":[113],"more":[114],"suitable":[115],"integration":[117],"industry-standard":[119],"pipelines.":[120],"Extensive":[121],"experimental":[122],"results":[123],"demonstrate":[124],"that":[125],"our":[126],"approach":[127],"significantly":[128],"outperforms":[129],"state-of-the-art":[131],"terms":[134],"both":[136],"accuracy.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
