{"id":"https://openalex.org/W4400818936","doi":"https://doi.org/10.1145/3658221","title":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","display_name":"DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400818936","doi":"https://doi.org/10.1145/3658221"},"language":"en","primary_location":{"id":"doi:10.1145/3658221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658221","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3658221","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021093689","display_name":"Zhiyao Sun","orcid":"https://orcid.org/0000-0002-6377-7103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyao Sun","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6377-7103","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103226758","display_name":"Tian Lv","orcid":"https://orcid.org/0000-0002-3726-0530"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Lv","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3726-0530","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002105309","display_name":"Sheng Ye","orcid":"https://orcid.org/0000-0001-9280-6279"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Ye","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9280-6279","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078405581","display_name":"Matthieu Gaetan Lin","orcid":"https://orcid.org/0009-0004-4265-6830"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Matthieu Lin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4265-6830","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086465547","display_name":"Jenny Sheng","orcid":"https://orcid.org/0009-0007-7863-8409"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jenny Sheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-7863-8409","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034005121","display_name":"Yu\u2010Hui Wen","orcid":"https://orcid.org/0000-0001-6195-9782"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Hui Wen","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6195-9782","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048662587","display_name":"Minjing Yu","orcid":"https://orcid.org/0000-0001-6755-2027"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjing Yu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-6755-2027","affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008076279","display_name":"Yong\u2010Jin Liu","orcid":"https://orcid.org/0000-0001-5774-1916"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Jin Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5774-1916","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.9827,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.99262519,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"43","issue":"4","first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9969000220298767,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.8674388527870178},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6117274761199951},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.5461798906326294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5418312549591064},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5298609137535095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5235176682472229},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4559505581855774},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.455194354057312},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4539213180541992},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4301583468914032},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.42800411581993103},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.3276817798614502},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32706016302108765},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.28753194212913513},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.28068262338638306},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11929237842559814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8674388527870178},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6117274761199951},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.5461798906326294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5418312549591064},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5298609137535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5235176682472229},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4559505581855774},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.455194354057312},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4539213180541992},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4301583468914032},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.42800411581993103},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3276817798614502},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32706016302108765},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28753194212913513},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.28068262338638306},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11929237842559814},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3658221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658221","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3658221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3658221","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3658221","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400818936.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2468212864","https://openalex.org/W2769666294","https://openalex.org/W2974067445","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W3209059054","https://openalex.org/W4221138280","https://openalex.org/W4226211505","https://openalex.org/W4226317937","https://openalex.org/W4296438045","https://openalex.org/W4372341521","https://openalex.org/W4377010269","https://openalex.org/W4380994134","https://openalex.org/W4386072021","https://openalex.org/W4386076103","https://openalex.org/W4386076250","https://openalex.org/W4389880093","https://openalex.org/W4390872742","https://openalex.org/W4390873123","https://openalex.org/W6600009415","https://openalex.org/W6631455383"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2018882065","https://openalex.org/W2532377291","https://openalex.org/W2121378366","https://openalex.org/W4310844315","https://openalex.org/W2999276620","https://openalex.org/W2617644139","https://openalex.org/W2379697716","https://openalex.org/W4210514273","https://openalex.org/W3169129874"],"abstract_inverted_index":{"The":[0,163],"generation":[1,104,118],"of":[2,60,119,131],"stylistic":[3],"3D":[4,133],"facial":[5,28],"animations":[6],"driven":[7],"by":[8,137],"speech":[9,109],"presents":[10],"a":[11,18,35,46,74,84,146],"significant":[12],"challenge":[13],"as":[14],"it":[15],"requires":[16],"learning":[17],"many-to-many":[19],"mapping":[20,40],"between":[21],"speech,":[22],"style,":[23],"and":[24,63,110,153,165],"the":[25,43,51,58,61,79,103,108,117,129],"corresponding":[26],"natural":[27],"motion.":[29],"However,":[30],"existing":[31],"methods":[32],"either":[33],"employ":[34,98],"deterministic":[36],"model":[37,81,140],"for":[38],"speech-to-motion":[39],"or":[41],"encode":[42],"style":[44,62,85,89,115],"using":[45],"one-hot":[47,52],"encoding":[48,53],"scheme.":[49],"Notably,":[50],"approach":[54,159],"fails":[55],"to":[56,101],"capture":[57],"complexity":[59],"thus":[64],"limits":[65],"generalization":[66],"ability.":[67],"In":[68,112],"this":[69],"paper,":[70],"we":[71,97,127],"propose":[72],"DiffPoseTalk,":[73],"generative":[75],"framework":[76],"based":[77,106],"on":[78,107,141],"diffusion":[80],"combined":[82],"with":[83],"encoder":[86],"that":[87,157],"extracts":[88],"embeddings":[90],"from":[91,145],"short":[92],"reference":[93],"videos.":[94],"During":[95],"inference,":[96],"classifier-free":[99],"guidance":[100],"guide":[102],"process":[105],"style.":[111],"particular,":[113],"our":[114,139,158],"includes":[116],"head":[120],"poses,":[121],"thereby":[122],"enhancing":[123],"user":[124,154],"perception.":[125],"Additionally,":[126],"address":[128],"shortage":[130],"scanned":[132],"talking":[134],"face":[135],"data":[136],"training":[138],"reconstructed":[142],"3DMM":[143],"parameters":[144],"high-quality,":[147],"in-the-wild":[148],"audio-visual":[149],"dataset.":[150],"Extensive":[151],"experiments":[152],"study":[155],"demonstrate":[156],"outperforms":[160],"state-of-the-art":[161],"methods.":[162],"code":[164],"dataset":[166],"are":[167],"at":[168],"https://diffposetalk.github.io.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":11}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}