{"id":"https://openalex.org/W7164168586","doi":"https://doi.org/10.1109/tvcg.2026.3702133","title":"EmoPoseFace: Head Pose Aware Speech-Driven 3D Emotional Facial Animation Using Latent Diffusion","display_name":"EmoPoseFace: Head Pose Aware Speech-Driven 3D Emotional Facial Animation Using Latent Diffusion","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164168586","doi":"https://doi.org/10.1109/tvcg.2026.3702133","pmid":"https://pubmed.ncbi.nlm.nih.gov/42268773"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3702133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3702133","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":["crossref","pubmed"],"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/A5003662421","display_name":"Xin Zhao","orcid":"https://orcid.org/0000-0002-7660-9897"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4071-1428","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107919524","display_name":"J. P. Dai","orcid":"https://orcid.org/0000-0002-9397-8539"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Dai","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9397-8539","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138356419","display_name":"Feng Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhou","raw_affiliation_strings":["North China University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9184-2040","affiliations":[{"raw_affiliation_string":"North China University of Technology, Beijing, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771231","display_name":"Haofei Wang","orcid":"https://orcid.org/0000-0002-1199-9206"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofei Wang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1199-9206","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138378771","display_name":"Zhen Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Song","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035153076","display_name":"Aimin Hao","orcid":"https://orcid.org/0000-0002-5774-6706"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Hao","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5774-6706","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091408797","display_name":"Hong Qin","orcid":"https://orcid.org/0000-0001-7699-1355"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Qin","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-7699-1355","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101489329","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-9149-3554"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9149-3554","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74355948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"8","first_page":"7631","last_page":"7644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9362999796867371,"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":0.9362999796867371,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.017000000923871994,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5587000250816345},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4724000096321106},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.444599986076355},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.384799987077713},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.3828999996185303},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.38280001282691956},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.38119998574256897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295000195503235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6783999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6700999736785889},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4724000096321106},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.42010000348091125},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.38280001282691956},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3637000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.30309998989105225},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.2727000117301941},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27070000767707825}],"mesh":[{"descriptor_ui":"D000095902","descriptor_name":"Avatar","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000095902","descriptor_name":"Avatar","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":false},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":false},{"descriptor_ui":"D005149","descriptor_name":"Facial Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005149","descriptor_name":"Facial Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006257","descriptor_name":"Head","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D006257","descriptor_name":"Head","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3702133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3702133","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:42268773","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42268773","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}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.40241894125938416,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G2131922534","display_name":null,"funder_award_id":"62202248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4880826994","display_name":null,"funder_award_id":"4252018","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8045388874","display_name":null,"funder_award_id":"62102208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8519059759","display_name":null,"funder_award_id":"62572032","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,77],"facial":[2,20,41,55,79,96,108,127,131,140,173],"animation":[3],"has":[4,58],"notable":[5],"applications":[6],"in":[7,151,182],"the":[8,48,115,135,168,176],"VR":[9],"domain,":[10],"including":[11],"virtual":[12,172],"anchors":[13],"and":[14,43,98,103,129,137,154,164,175],"digital":[15],"avatars,":[16],"etc.":[17],"However,":[18],"producing":[19],"animations":[21,80],"that":[22,145],"convey":[23],"complex":[24],"emotional":[25,45,56,78,124,155,171],"expressions":[26,97,128],"remains":[27],"a":[28,70,88],"substantial":[29],"challenge.":[30],"Existing":[31],"methods":[32,150],"struggle":[33],"to":[34,74,93],"simultaneously":[35],"achieve":[36],"accurate":[37],"lip":[38],"synchronization,":[39],"natural":[40],"expressions,":[42],"realistic":[44],"representation.":[46],"Significantly,":[47],"impact":[49],"of":[50,126,139,160,170],"head":[51,83,99,161],"pose":[52,162],"on":[53],"boosting":[54],"expressiveness":[57,169],"not":[59],"been":[60],"thoroughly":[61],"investigated.":[62],"To":[63],"address":[64],"these":[65],"issues,":[66],"we":[67,113],"propose":[68],"EmoPoseFace,":[69],"novel":[71],"Diffusion-based":[72],"network":[73],"generate":[75],"speech-driven":[76],"with":[81],"synchronized":[82],"poses.":[84],"Our":[85],"method":[86],"employs":[87],"dual-branch":[89],"conditional":[90],"generation":[91],"architecture":[92],"separately":[94],"model":[95],"poses,":[100],"integrating":[101],"emotion":[102],"head-pose":[104],"conditions":[105],"for":[106],"coherent":[107],"expression-pose":[109],"control.":[110],"In":[111],"addition,":[112],"design":[114],"Global-local":[116],"Facial":[117],"Fine-grained":[118],"Editing":[119],"Module":[120],"(GL-FFE),":[121],"which":[122],"achieves":[123],"enhancement":[125],"fine-grained":[130,177],"modification,":[132],"while":[133],"maintains":[134],"naturalness":[136],"authenticity":[138],"movements.":[141],"Extensive":[142],"experiments":[143],"demonstrate":[144],"our":[146],"approach":[147],"outperforms":[148],"existing":[149],"lip-sync":[152],"accuracy":[153],"detail":[156],"preservation.":[157],"The":[158],"introduction":[159],"control":[163],"GL-FFE":[165],"significantly":[166],"expands":[167],"animation,":[174],"editing":[178],"is":[179],"widely":[180],"approved":[181],"perceptual":[183],"user":[184],"studies.":[185]},"counts_by_year":[],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-06-11T00:00:00"}
