{"id":"https://openalex.org/W7123369018","doi":"https://doi.org/10.1109/tvcg.2026.3651640","title":"ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting","display_name":"ESGaussianFace: Emotional and Stylized Audio-Driven Facial Animation via 3D Gaussian Splatting","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123369018","doi":"https://doi.org/10.1109/tvcg.2026.3651640","pmid":"https://pubmed.ncbi.nlm.nih.gov/41525576"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3651640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3651640","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.01847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121840579","display_name":"Chuhang Ma","orcid":null},"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":true,"raw_author_name":"Chuhang Ma","raw_affiliation_strings":["State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122865521","display_name":"Shuai Tan","orcid":null},"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":["State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"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":["State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Micro-Nano Engineering Science and John Hopcroft Center, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122906367","display_name":"Xin Tong","orcid":null},"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":"Xin Tong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5121840579"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07806452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"3","first_page":"2659","last_page":"2670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7912999987602234,"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":0.7912999987602234,"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":0.16269999742507935,"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":0.01140000019222498,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.7871999740600586},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.640500009059906},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5601000189781189},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5056999921798706},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.447299987077713},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4377000033855438},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.40790000557899475},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.39489999413490295},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36489999294281006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567000031471252},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.7871999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6416000127792358},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5601000189781189},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.2632000148296356},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tvcg.2026.3651640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3651640","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:41525576","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41525576","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},{"id":"pmh:oai:arXiv.org:2601.01847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.01847","pdf_url":"https://arxiv.org/pdf/2601.01847","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.01847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.01847","pdf_url":"https://arxiv.org/pdf/2601.01847","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"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"},{"id":"https://openalex.org/G8758788065","display_name":null,"funder_award_id":"62102255","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0],"current":[1],"audio-driven":[2,59],"facial":[3,22,60,107],"animation":[4],"research":[5],"primarily":[6],"focuses":[7],"on":[8],"generating":[9,29],"videos":[10,23,33],"with":[11,94],"neutral":[12],"emotions.":[13],"While":[14],"some":[15],"studies":[16],"have":[17],"addressed":[18],"the":[19,101,122,146,150],"generation":[20,77],"of":[21,78,121,149,183],"driven":[24],"by":[25],"emotional":[26,37,56,111,117,154],"audio,":[27],"efficiently":[28],"high-quality":[30],"talking":[31],"head":[32],"that":[34,89,174],"integrate":[35],"both":[36],"expressions":[38],"and":[39,57,72,118,128,156,167,189],"style":[40,129,157,190],"features":[41,93],"remains":[42],"a":[43,141],"significant":[44],"challenge.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,131,139],"propose":[50,83,140],"ESGaussianFace,":[51],"an":[52,84],"innovative":[53],"framework":[54],"for":[55],"stylized":[58,119],"animation.":[61],"Our":[62,159],"approach":[63],"leverages":[64],"3D":[65,70,79,123,134,168],"Gaussian":[66,124,135],"Splatting":[67],"to":[68,105],"reconstruct":[69,106],"scenes":[71],"render":[73],"videos,":[74],"ensuring":[75],"efficient":[76],"consistent":[80],"results.":[81],"We":[82],"emotion-audio-guided":[85],"spatial":[86],"attention":[87],"method":[88,176],"effectively":[90],"integrates":[91],"emotion":[92,127],"audio":[95],"content":[96],"features.":[97,158],"Through":[98],"emotion-guided":[99],"attention,":[100],"model":[102],"is":[103],"able":[104],"details":[108],"across":[109],"different":[110],"states":[112],"more":[113],"accurately.":[114],"To":[115],"achieve":[116],"deformations":[120],"points":[125],"through":[126],"features,":[130],"introduce":[132],"two":[133],"deformation":[136],"predictors.":[137],"Futhermore,":[138],"multi-stage":[142],"training":[143],"strategy,":[144],"enabling":[145],"step-by-step":[147],"learning":[148],"character's":[151],"lip":[152,184],"movements,":[153],"variations,":[155],"generated":[160],"results":[161,172],"exhibit":[162],"high":[163,165],"efficiency,":[164],"quality,":[166],"consistency.":[169],"Extensive":[170],"experimental":[171],"demonstrate":[173],"our":[175],"outperforms":[177],"existing":[178],"state-of-the-art":[179],"techniques":[180],"in":[181],"terms":[182],"movement":[185],"accuracy,":[186],"expression":[187],"variation,":[188],"feature":[191],"expressiveness.":[192]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}