{"id":"https://openalex.org/W4404450558","doi":"https://doi.org/10.48550/arxiv.2411.09209","title":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","display_name":"JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404450558","doi":"https://doi.org/10.48550/arxiv.2411.09209"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.09209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.09209","pdf_url":"https://arxiv.org/pdf/2411.09209","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.09209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cao, Xuyang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xuyang","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Guoxin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoxin","raw_affiliation_strings":["Zhejiang University JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101461086","display_name":"Sheng Shi","orcid":"https://orcid.org/0009-0002-3573-8104","observed_orcids":["https://orcid.org/0009-0002-3573-8104"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Sheng","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610488","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0002-1266-415X","observed_orcids":["https://orcid.org/0000-0002-1266-415X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jun","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651972","display_name":"Yao Yang","orcid":"https://orcid.org/0000-0002-0261-5020","observed_orcids":["https://orcid.org/0000-0002-0261-5020"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yang","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037558114","display_name":"Jintao Fei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei, Jintao","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gao, Minyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Minyu","raw_affiliation_strings":["JD Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Health International Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Xie, Pei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pei","raw_affiliation_strings":["Health International Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health International Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8446999788284302,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8446999788284302,"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/T11448","display_name":"Face recognition and analysis","score":0.0843999981880188,"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":0.045099999755620956,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/diffusion-transformer","display_name":"diffusion transformer","score":0.75},{"id":"https://openalex.org/keywords/facial-dynamics","display_name":"facial dynamics","score":0.49399998784065247}],"concepts":[{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7795099020004272},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6543936729431152},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.601222038269043},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5482075214385986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5457479357719421},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5454477071762085},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5241625308990479},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5155458450317383},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5054283142089844},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4841395318508148},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4254700243473053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196200966835022},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.33034080266952515},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3206717073917389},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17077183723449707},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.1652715802192688},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08062192797660828},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06670266389846802},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.09209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.09209","pdf_url":"https://arxiv.org/pdf/2411.09209","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.09209","doi":"https://doi.org/10.48550/arxiv.2411.09209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.09209","pdf_url":null,"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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.09209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.09209","pdf_url":"https://arxiv.org/pdf/2411.09209","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404450558.pdf","grobid_xml":"https://content.openalex.org/works/W4404450558.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4367701091","https://openalex.org/W4388684923","https://openalex.org/W4389911993","https://openalex.org/W4390438010","https://openalex.org/W4393248189","https://openalex.org/W4400376721","https://openalex.org/W4403364748","https://openalex.org/W4403555388","https://openalex.org/W4403755228","https://openalex.org/W4413147584","https://openalex.org/W4413557526","https://openalex.org/W4415799309"],"related_works":["https://openalex.org/W4393248189","https://openalex.org/W4412477709","https://openalex.org/W4399695531","https://openalex.org/W4409366237","https://openalex.org/W4403995699","https://openalex.org/W4390874181","https://openalex.org/W6948098213","https://openalex.org/W4412408182","https://openalex.org/W4413147005","https://openalex.org/W4413146352"],"abstract_inverted_index":{"Audio-driven":[0],"portrait":[1,213],"animation":[2],"has":[3,23],"made":[4],"significant":[5],"advances":[6],"with":[7,99],"diffusion-based":[8,48],"models,":[9],"improving":[10,201],"video":[11,36],"quality":[12],"and":[13,29,38,54,138,154,181,204],"lipsync":[14],"accuracy.":[15],"However,":[16],"the":[17,63,86,105,130,134,139,150,155,191,210],"increasing":[18],"complexity":[19],"of":[20,122,178,193],"these":[21],"models":[22],"led":[24],"to":[25,88,113,145,165],"inefficiencies":[26],"in":[27,57,62,104,129,212],"training":[28],"inference,":[30],"as":[31,33,143],"well":[32],"constraints":[34],"on":[35,174,200],"length":[37],"inter-frame":[39],"continuity.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,66],"propose":[45],"JoyVASA,":[46],"a":[47,68,108,126,175],"method":[49],"for":[50],"generating":[51],"facial":[52,59,70,76,81,97,136,152],"dynamics":[53],"head":[55],"motion":[56,101,115,141,157],"audio-driven":[58],"animation.":[60,214],"Specifically,":[61],"first":[64,131],"stage,":[65,107],"introduce":[67],"decoupled":[69,151],"representation":[71,98,137,153],"framework":[72],"that":[73],"separates":[74],"dynamic":[75,100],"expressions":[77],"from":[78,118],"static":[79,95],"3D":[80,96,135],"representations.":[82],"This":[83],"decoupling":[84],"allows":[85],"system":[87],"generate":[89,114],"longer":[90],"videos":[91],"by":[92],"combining":[93],"any":[94],"sequences.":[102],"Then,":[103],"second":[106],"diffusion":[109],"transformer":[110],"is":[111,172,217],"trained":[112,128,173],"sequences":[116,142],"directly":[117],"audio":[119],"cues,":[120],"independent":[121],"character":[123],"identity.":[124],"Finally,":[125],"generator":[127],"stage":[132],"uses":[133],"generated":[140],"inputs":[144],"render":[146],"high-quality":[147],"animations.":[148],"With":[149],"identity-independent":[156],"generation":[158],"process,":[159],"JoyVASA":[160],"extends":[161],"beyond":[162],"human":[163],"portraits":[164],"animate":[166],"animal":[167],"faces":[168],"seamlessly.":[169],"The":[170,215],"model":[171],"hybrid":[176],"dataset":[177],"private":[179],"Chinese":[180],"public":[182],"English":[183],"data,":[184],"enabling":[185],"multilingual":[186],"support.":[187],"Experimental":[188],"results":[189],"validate":[190],"effectiveness":[192],"our":[194],"approach.":[195],"Future":[196],"work":[197],"will":[198],"focus":[199],"real-time":[202],"performance":[203],"refining":[205],"expression":[206],"control,":[207],"further":[208],"expanding":[209],"applications":[211],"code":[216],"available":[218],"at:":[219],"https://github.com/jdh-algo/JoyVASA.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-17T00:00:00"}
