{"id":"https://openalex.org/W4415428178","doi":"https://doi.org/10.3233/faia251193","title":"APasco: High Fidelity Audio-Driven Portrait Animation Based on Audio-Lip Multi-Head Cross-Attention and 3D Dense Geometric Prior","display_name":"APasco: High Fidelity Audio-Driven Portrait Animation Based on Audio-Lip Multi-Head Cross-Attention and 3D Dense Geometric Prior","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428178","doi":"https://doi.org/10.3233/faia251193"},"language":null,"primary_location":{"id":"doi:10.3233/faia251193","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251193","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251193","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102946449","display_name":"Jinhan Xie","orcid":"https://orcid.org/0000-0002-9762-4826"},"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"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinhan Xie","raw_affiliation_strings":["Pengcheng Laboratory","School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004007577","display_name":"Kanglin Liu","orcid":"https://orcid.org/0000-0002-6293-5464"},"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":"Kanglin Liu","raw_affiliation_strings":["Pengcheng Laboratory"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090395727","display_name":"Zhenyu Bao","orcid":"https://orcid.org/0000-0003-1368-9364"},"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"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Bao","raw_affiliation_strings":["Pengcheng Laboratory","School of Electronic and Computer Engineering, Peking University"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404129","display_name":"Qing Li","orcid":"https://orcid.org/0000-0002-7816-9733"},"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":"Qing Li","raw_affiliation_strings":["Pengcheng Laboratory"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102946449"],"corresponding_institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7601461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10860","display_name":"Speech and Audio Processing","score":0.9855999946594238,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9855999946594238,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9550999999046326,"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/T12290","display_name":"Human Motion and Animation","score":0.9466999769210815,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6437000036239624},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5234000086784363},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.451200008392334},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3734999895095825},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3537999987602234},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.35339999198913574},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3490999937057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225000262260437},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5877000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760999917984009},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5454000234603882},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.451200008392334},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.2549000084400177},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251193","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251193","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251193","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251193","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"Audio-driven":[0],"portrait":[1],"animation":[2],"has":[3],"achieved":[4],"significant":[5],"advances":[6],"propelled":[7],"by":[8,45,62],"the":[9,73,81,98],"development":[10],"of":[11],"diffusion":[12,23],"models.":[13],"Despite":[14],"remarkable":[15],"improvements":[16],"in":[17,114],"driving":[18],"capability":[19],"and":[20,31,51,118,128],"temporal":[21],"consistency,":[22],"model-based":[24],"methods":[25],"still":[26],"suffer":[27],"from":[28,92],"audio-lip":[29,49],"misalignment":[30],"facial":[32,82],"detail":[33,130],"loss.":[34],"To":[35,79],"address":[36],"them,":[37],"we":[38,58,85],"present":[39],"a":[40],"novel":[41],"stable":[42],"diffusion-based":[43],"approach":[44],"conditioning":[46],"on":[47,105],"aligned":[48],"features":[50,67,91],"3D":[52,87,93],"dense":[53,88,94],"sequential":[54,89],"geometry":[55,90],"features.":[56],"Specifically,":[57],"enhance":[59],"phoneme-lip":[60],"synchronization":[61],"coupling":[63],"fine-grained":[64],"local":[65,83],"lip":[66],"with":[68,72],"corresponding":[69],"audio":[70],"details":[71],"designed":[74],"Audio-Lip":[75],"multi-head":[76],"Cross-Attention":[77],"module.":[78],"improve":[80],"details,":[84],"derive":[86],"geometric":[95],"prior":[96],"via":[97],"developed":[99],"Mesh":[100],"Spatio-Temporal":[101],"Encoder.":[102],"Extensive":[103],"experiments":[104],"public":[106],"benchmarks":[107],"demonstrate":[108],"that":[109],"APasco":[110],"achieves":[111],"superior":[112],"performance":[113],"both":[115],"visual":[116],"quality":[117],"lip-sync":[119],"accuracy":[120],"compared":[121],"to":[122],"existing":[123],"approaches.":[124],"Further":[125],"supplementary":[126],"material":[127],"project":[129],"can":[131],"be":[132],"found":[133],"at:":[134],"https://github.com/xiejinhan0428/APasco.":[135]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
