{"id":"https://openalex.org/W4403576235","doi":"https://doi.org/10.48550/arxiv.2410.10122","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","display_name":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4403576235","doi":"https://doi.org/10.48550/arxiv.2410.10122"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.10122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.10122","pdf_url":"https://arxiv.org/pdf/2410.10122","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":"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"},"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/2410.10122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100333731","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5448-7286","observed_orcids":["https://orcid.org/0000-0002-5448-7286"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yue","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhong, Zhizhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Zhizhou","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102803711","display_name":"Minhao Liu","orcid":"https://orcid.org/0000-0003-4120-2269","observed_orcids":["https://orcid.org/0000-0003-4120-2269"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Minhao","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050788637","display_name":"Zhaokang Chen","orcid":"https://orcid.org/0000-0003-0237-0358","observed_orcids":["https://orcid.org/0000-0003-0237-0358"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhaokang","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512417","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0003-0657-3427","observed_orcids":["https://orcid.org/0000-0003-0657-3427"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Bin","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032766531","display_name":"Yubin Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Yubin","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhan, Chao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan, Chao","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment","The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004311668","display_name":"Yingjie He","orcid":"https://orcid.org/0000-0002-3305-2486","observed_orcids":["https://orcid.org/0000-0002-3305-2486"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Yingjie","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Junxin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Junxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhou, Wenjiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Wenjiang","raw_affiliation_strings":["Lyra Lab , Tencent Music Entertainment"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lyra Lab , Tencent Music Entertainment","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":63,"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":0.9955999851226807,"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":0.9955999851226807,"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/T10860","display_name":"Speech and Audio Processing","score":0.0026000000070780516,"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":0.0008999999845400453,"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/lip-synchronization","display_name":"lip synchronization","score":0.9539999961853027},{"id":"https://openalex.org/keywords/identity-consistency","display_name":"identity consistency","score":0.7139999866485596},{"id":"https://openalex.org/keywords/spatiotemporal-sampling","display_name":"spatiotemporal sampling","score":0.8880000114440918},{"id":"https://openalex.org/keywords/latent-space-optimization","display_name":"latent space optimization","score":0.7009999752044678},{"id":"https://openalex.org/keywords/audio-visual-feature-fusion","display_name":"audio-visual feature fusion","score":0.9380000233650208},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.6190000176429749}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9138803482055664},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5411649346351624},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5131388306617737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5083982348442078},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4413762390613556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37997743487358093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37596040964126587},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17788338661193848},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08852189779281616},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0729178786277771},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.10122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.10122","pdf_url":"https://arxiv.org/pdf/2410.10122","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":"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"},{"id":"doi:10.48550/arxiv.2410.10122","doi":"https://doi.org/10.48550/arxiv.2410.10122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.10122","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.10122","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.10122","pdf_url":"https://arxiv.org/pdf/2410.10122","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":"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403576235.pdf","grobid_xml":"https://content.openalex.org/works/W4403576235.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2908510526","https://openalex.org/W4383994075","https://openalex.org/W4399424746","https://openalex.org/W4399695531","https://openalex.org/W4400376721","https://openalex.org/W4405355109","https://openalex.org/W4407713144","https://openalex.org/W4409369524","https://openalex.org/W4411049949"],"related_works":["https://openalex.org/W4390874172","https://openalex.org/W4406231552","https://openalex.org/W7203861064","https://openalex.org/W7117536388","https://openalex.org/W7154465078","https://openalex.org/W4402980265","https://openalex.org/W4404965718","https://openalex.org/W3205904637","https://openalex.org/W4309633564","https://openalex.org/W7160840134"],"abstract_inverted_index":{"Real-time":[0],"video":[1],"dubbing":[2],"that":[3,53,150],"preserves":[4],"identity":[5,94],"consistency":[6],"while":[7,33,92,158],"achieving":[8,159],"accurate":[9],"lip":[10],"synchronization":[11,118],"remains":[12],"a":[13,19,48],"critical":[14],"challenge.":[15],"Existing":[16],"approaches":[17],"face":[18],"trilemma:":[20],"diffusion-based":[21],"methods":[22,154],"achieve":[23],"high":[24],"visual":[25,156],"fidelity":[26,157],"but":[27],"suffer":[28],"from":[29],"prohibitive":[30],"computational":[31],"costs,":[32],"GAN-based":[34],"solutions":[35],"sacrifice":[36],"lip-sync":[37,161],"accuracy":[38],"or":[39],"dental":[40,120],"details":[41],"for":[42],"real-time":[43],"performance.":[44],"We":[45],"present":[46],"MuseTalk,":[47],"novel":[49],"two-stage":[50],"training":[51],"framework":[52,130],"resolves":[54],"this":[55],"trade-off":[56],"through":[57],"latent":[58,133],"space":[59],"optimization":[60],"and":[61,119,165],"spatio-temporal":[62],"data":[63],"sampling":[64],"strategy.":[65],"Our":[66],"key":[67],"innovations":[68],"include:":[69],"(1)":[70],"During":[71],"the":[72,98,111,132],"Facial":[73],"Abstract":[74],"Pretraining":[75],"stage,":[76,102],"we":[77,103],"propose":[78],"Informative":[79],"Frame":[80],"Sampling":[81,107],"to":[82,108],"temporally":[83],"align":[84],"reference-source":[85],"pose":[86],"pairs,":[87],"eliminating":[88],"redundant":[89],"feature":[90,128],"interference":[91],"preserving":[93],"cues.":[95],"(2)":[96],"In":[97],"Lip-Sync":[99],"Adversarial":[100],"Finetuning":[101],"employ":[104],"Dynamic":[105],"Margin":[106],"spatially":[109],"select":[110],"most":[112],"suitable":[113],"lip-movement-promoting":[114],"regions,":[115],"balancing":[116],"audio-visual":[117,127],"clarity.":[121],"(3)":[122],"MuseTalk":[123,151],"establishes":[124],"an":[125,143],"effective":[126],"fusion":[129],"in":[131,155],"space,":[134],"delivering":[135],"30":[136],"FPS":[137],"output":[138],"at":[139,179],"256*256":[140],"resolution":[141],"on":[142],"NVIDIA":[144],"V100":[145],"GPU.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"outperforms":[152],"state-of-the-art":[153],"comparable":[160],"accuracy.":[162],"%The":[163],"codes":[164],"models":[166],"will":[167],"be":[168],"made":[169,177],"publicly":[170],"available":[171,178],"upon":[172],"acceptance.":[173],"The":[174],"code":[175],"is":[176],"\\href{https://github.com/TMElyralab/MuseTalk}{https://github.com/TMElyralab/MuseTalk}":[180]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-20T00:00:00"}