{"id":"https://openalex.org/W4389217725","doi":"https://doi.org/10.48550/arxiv.2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","display_name":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","publication_year":2023,"publication_date":"2023-11-29","ids":{"openalex":"https://openalex.org/W4389217725","doi":"https://doi.org/10.48550/arxiv.2311.17590"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.17590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.17590","pdf_url":"https://arxiv.org/pdf/2311.17590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.17590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062816933","display_name":"Ziqiao Peng","orcid":"https://orcid.org/0009-0000-1341-9618"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng, Ziqiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044682092","display_name":"Wentao Hu","orcid":"https://orcid.org/0000-0001-8495-4175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Wentao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109801552","display_name":"Yue Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632822","display_name":"Xiangyu Zhu","orcid":"https://orcid.org/0000-0002-4636-9677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352991","display_name":"Xiaomei Zhang","orcid":"https://orcid.org/0000-0002-0221-6978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaomei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110988253","display_name":"Hao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766736","display_name":"Jun He","orcid":"https://orcid.org/0000-0002-3017-2108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332465","display_name":"Hongyan Liu","orcid":"https://orcid.org/0000-0002-4902-1078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hongyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021141988","display_name":"Zhaoxin Fan","orcid":"https://orcid.org/0000-0002-6324-1712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Zhaoxin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5062816933"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11448","display_name":"Face recognition and analysis","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9803000092506409,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9178000092506409,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7514114379882812},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6928149461746216},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.5904457569122314},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5766215920448303},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5320329070091248},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4698335826396942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42791587114334106},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4176207482814789},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38882583379745483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3768927752971649},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.14643961191177368},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11287707090377808},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.1007387638092041},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07508501410484314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514114379882812},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6928149461746216},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.5904457569122314},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5766215920448303},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5320329070091248},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4698335826396942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42791587114334106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4176207482814789},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38882583379745483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3768927752971649},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.14643961191177368},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11287707090377808},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.1007387638092041},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07508501410484314},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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:2311.17590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.17590","pdf_url":"https://arxiv.org/pdf/2311.17590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.17590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.17590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.17590","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.17590","pdf_url":"https://arxiv.org/pdf/2311.17590","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5480676819","display_name":null,"funder_award_id":"62072459","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5621106950","display_name":null,"funder_award_id":"6207245","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"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389217725.pdf","grobid_xml":"https://content.openalex.org/works/W4389217725.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1995263003","https://openalex.org/W2222580448","https://openalex.org/W4206700937","https://openalex.org/W1971708112"],"abstract_inverted_index":{"Achieving":[0],"high":[1],"synchronization":[2,110,183],"in":[3,94,113,182],"the":[4,85,92,160,164,189],"synthesis":[5],"of":[6,58,70,88],"realistic,":[7],"speech-driven":[8],"talking":[9,53,97,114],"head":[10,49,54,66,115,145,150,162],"videos":[11],"presents":[12],"a":[13,74,119,131,167],"significant":[14],"challenge.":[15],"Traditional":[16],"Generative":[17],"Adversarial":[18],"Networks":[19],"(GAN)":[20],"struggle":[21],"to":[22,78,122,136],"maintain":[23],"consistent":[24],"facial":[25,45,63,133,139],"identity,":[26,60,108],"while":[27],"Neural":[28],"Radiance":[29],"Fields":[30],"(NeRF)":[31],"methods,":[32],"although":[33],"they":[34],"can":[35],"address":[36,84],"this":[37],"issue,":[38],"often":[39],"produce":[40],"mismatched":[41],"lip":[42,61,124],"movements,":[43,62],"inadequate":[44],"expressions,":[46,64],"and":[47,65,80,111,128,158,173,184],"unstable":[48],"poses.":[50,67],"A":[51],"lifelike":[52],"requires":[55],"synchronized":[56],"coordination":[57],"subject":[59,107],"The":[68,152],"absence":[69],"these":[71],"synchronizations":[72],"is":[73],"fundamental":[75],"flaw,":[76],"leading":[77],"unrealistic":[79],"artificial":[81],"outcomes.":[82],"To":[83],"critical":[86],"issue":[87],"synchronization,":[89],"identified":[90],"as":[91],"\"devil\"":[93],"creating":[95],"realistic":[96],"heads,":[98],"we":[99],"introduce":[100],"SyncTalk.":[101],"This":[102],"NeRF-based":[103],"method":[104],"effectively":[105],"maintains":[106],"enhancing":[109],"realism":[112],"synthesis.":[116],"SyncTalk":[117,178],"employs":[118],"Face-Sync":[120],"Controller":[121],"align":[123],"movements":[125],"with":[126,163],"speech":[127],"innovatively":[129],"uses":[130],"3D":[132],"blendshape":[134],"model":[135],"capture":[137],"accurate":[138],"expressions.":[140],"Our":[141],"Head-Sync":[142],"Stabilizer":[143],"optimizes":[144],"poses,":[146],"achieving":[147],"more":[148],"natural":[149],"movements.":[151],"Portrait-Sync":[153],"Generator":[154],"restores":[155],"hair":[156],"details":[157],"blends":[159],"generated":[161],"torso":[165],"for":[166],"seamless":[168],"visual":[169],"experience.":[170],"Extensive":[171],"experiments":[172],"user":[174],"studies":[175],"demonstrate":[176],"that":[177],"outperforms":[179],"state-of-the-art":[180],"methods":[181],"realism.":[185],"We":[186],"recommend":[187],"watching":[188],"supplementary":[190],"video:":[191],"https://ziqiaopeng.github.io/synctalk":[192]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
