{"id":"https://openalex.org/W4414359977","doi":"https://doi.org/10.24963/ijcai.2025/185","title":"SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation","display_name":"SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359977","doi":"https://doi.org/10.24963/ijcai.2025/185"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/185","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5014275363","display_name":"Yujian Liu","orcid":"https://orcid.org/0000-0002-7556-1924"},"institutions":[{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yujian Liu","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China","South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]},{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053440109","display_name":"Shidang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shidang Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044228369","display_name":"Jing Guo","orcid":"https://orcid.org/0000-0001-6752-6064"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jing Guo","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China","Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]},{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070395180","display_name":"Daosheng WANG","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dingbin Wang","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China","Beijing University Of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]},{"raw_affiliation_string":"Beijing University Of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115587768","display_name":"Zairan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zairan Wang","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086149782","display_name":"Xianfeng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianfeng Tan","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100610901","display_name":"Xiaoli Liu","orcid":"https://orcid.org/0000-0001-7763-2274"},"institutions":[{"id":"https://openalex.org/I2799969541","display_name":"The Art Institutes","ror":"https://ror.org/01p2ej961","country_code":"US","type":"education","lineage":["https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoli Liu","raw_affiliation_strings":["AiShiWeiLai AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AiShiWeiLai AI Research, Beijing, China","institution_ids":["https://openalex.org/I2799969541"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1657","last_page":"1665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9878000020980835,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/avatar","display_name":"Avatar","score":0.7713000178337097},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6717000007629395},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5814999938011169},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5446000099182129},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5300999879837036},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.46309998631477356},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4223000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79339998960495},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.7713000178337097},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6717000007629395},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5703999996185303},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5446000099182129},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5300999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C2992583082","wikidata":"https://www.wikidata.org/wiki/Q9645","display_name":"Upper body","level":3,"score":0.3862000107765198},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C9751117","wikidata":"https://www.wikidata.org/wiki/Q17105103","display_name":"Optical head-mounted display","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/185","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"talking":[1],"avatar":[2,82],"driven":[3],"by":[4,83],"audio":[5],"remains":[6],"a":[7],"significant":[8],"challenge.":[9],"Existing":[10],"methods":[11,41],"typically":[12],"require":[13],"high":[14,32],"computational":[15],"costs":[16],"and":[17,23,35,55,77,88,95,102,111,125,128],"often":[18],"lack":[19],"sufficient":[20],"facial":[21,53],"detail":[22],"realism,":[24],"making":[25],"them":[26],"unsuitable":[27],"for":[28],"applications":[29],"that":[30,73],"demand":[31],"real-time":[33,78],"performance":[34],"visual":[36],"quality.":[37],"Additionally,":[38],"while":[39],"some":[40],"can":[42,135],"synchronize":[43],"lip":[44,112],"movement,":[45,58],"they":[46],"still":[47],"face":[48],"issues":[49],"with":[50],"consistency":[51],"between":[52],"expressions":[54],"upper":[56,108,126],"body":[57],"particularly":[59],"during":[60],"silent":[61],"periods.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"introduce":[67],"SyncAnimation,":[68],"the":[69,115,123],"first":[70],"NeRF-based":[71],"method":[72],"achieves":[74,99,129],"audio-driven,":[75],"stable,":[76],"generation":[79],"of":[80,122],"speaking":[81],"combining":[84],"generalized":[85],"audio-to-pose":[86],"matching":[87],"audio-to-expression":[89],"synchronization.":[90],"By":[91],"integrating":[92],"AudioPose":[93],"Syncer":[94],"AudioEmotion":[96],"Syncer,":[97],"SyncAnimation":[98],"high-precision":[100],"poses":[101],"expression":[103],"generation,":[104],"progressively":[105],"producing":[106],"audio-synchronized":[107],"body,":[109,127],"head,":[110],"shapes.":[113],"Furthermore,":[114],"High-Synchronization":[116],"Human":[117],"Renderer":[118],"ensures":[119],"seamless":[120],"integration":[121],"head":[124],"audio-sync":[130],"lip.":[131],"The":[132],"project":[133],"page":[134],"be":[136],"found":[137],"at":[138],"https://syncanimation.github.io.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
