{"id":"https://openalex.org/W4415541033","doi":"https://doi.org/10.1145/3746027.3755671","title":"FLAP: Fully-controllable Audio-driven Portrait Video Generation through 3D head conditioned diffusion model","display_name":"FLAP: Fully-controllable Audio-driven Portrait Video Generation through 3D head conditioned diffusion model","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541033","doi":"https://doi.org/10.1145/3746027.3755671"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755671","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755671","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755671","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048241387","display_name":"Libing Mu","orcid":"https://orcid.org/0009-0001-0184-0664"},"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":"Lingzhou Mu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0184-0664","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010728849","display_name":"Baiji Liu","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":"Baiji Liu","raw_affiliation_strings":["South China University of Technology, guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-8102-9015","affiliations":[{"raw_affiliation_string":"South China University of Technology, guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruonan Zhang","orcid":"https://orcid.org/0009-0004-7960-2588"},"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":"Ruonan Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-7960-2588","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guiming Mo","orcid":"https://orcid.org/0009-0009-8658-5348"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiming Mo","raw_affiliation_strings":["XVERSE Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-8658-5348","affiliations":[{"raw_affiliation_string":"XVERSE Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiawei Jin","orcid":"https://orcid.org/0009-0001-3501-3034"},"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":"Jiawei Jin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-3501-3034","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101871787","display_name":"Kai Zhang","orcid":"https://orcid.org/0000-0002-5826-3765"},"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":"Kai Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5826-3765","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027959479","display_name":"Haozhi Huang","orcid":"https://orcid.org/0000-0003-3925-0237"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhi Huang","raw_affiliation_strings":["XVERSE Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3925-0237","affiliations":[{"raw_affiliation_string":"XVERSE Technology, Shenzhen, China","institution_ids":["https://openalex.org/I158809036"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10437","last_page":"10446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9975000023841858,"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":0.9627000093460083,"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/naturalness","display_name":"Naturalness","score":0.8325999975204468},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.4359999895095825},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4323999881744385},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.40299999713897705},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.3871000111103058},{"id":"https://openalex.org/keywords/active-appearance-model","display_name":"Active appearance model","score":0.3691999912261963},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.362199991941452},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3506999909877777}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8325999975204468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415000200271606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6148999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934000015258789},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.4359999895095825},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4058000147342682},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.27140000462532043},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755671","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755671","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755671","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755671","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2769666294","https://openalex.org/W2944294033","https://openalex.org/W3018564516","https://openalex.org/W3019952993","https://openalex.org/W3035719652","https://openalex.org/W3087121792","https://openalex.org/W3096831136","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W4200630629","https://openalex.org/W4304014863","https://openalex.org/W4312590328","https://openalex.org/W4312933868","https://openalex.org/W4380994134","https://openalex.org/W4386066404","https://openalex.org/W4386072021","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076250","https://openalex.org/W4390872297","https://openalex.org/W4390872742","https://openalex.org/W4390872774","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4393148505","https://openalex.org/W4400573497","https://openalex.org/W4400818936","https://openalex.org/W4402716181","https://openalex.org/W4402753521","https://openalex.org/W4404965490"],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"video":[1,162],"generation":[2,70,139],"techniques":[3],"have":[4],"significantly":[5],"improved":[6],"zero-shot":[7],"talking-head":[8],"avatar":[9],"generation,":[10],"enhancing":[11],"the":[12,65,79,103,122,142],"naturalness":[13,166],"of":[14,71,105,115,120],"both":[15,121,165],"head":[16,96,106,138],"motion":[17],"and":[18,38,61,99,108,125,148,167],"facial":[19,62,109,126],"expressions.":[20,127],"However,":[21],"existing":[22,136],"methods":[23],"suffer":[24],"from":[25,86],"poor":[26],"controllability,":[27],"making":[28],"them":[29],"less":[30],"applicable":[31],"to":[32,81],"real-world":[33],"scenarios":[34],"such":[35,94],"as":[36,95],"filmmaking":[37],"live":[39],"streaming":[40],"for":[41,68,112],"e-commerce.":[42],"To":[43],"address":[44],"this":[45],"limitation,":[46],"we":[47],"propose":[48],"FLAP,":[49],"a":[50],"novel":[51],"approach":[52],"that":[53,155],"integrates":[54],"explicit":[55],"3D":[56,137,145],"intermediate":[57],"parameters":[58],"(head":[59],"poses":[60],"expressions)":[63],"into":[64],"diffusion":[66,150],"model":[67,80],"end-to-end":[69,149],"realistic":[72],"portrait":[73,84,161],"videos.":[74],"The":[75],"proposed":[76],"architecture":[77],"allows":[78,111],"generate":[82],"vivid":[83],"videos":[85],"audio":[87],"while":[88],"simultaneously":[89],"incorporating":[90],"additional":[91],"control":[92,114],"signals,":[93],"rotation":[97],"angles":[98],"eye-blinking":[100],"frequency.":[101],"Furthermore,":[102],"decoupling":[104],"pose":[107,124],"expression":[110],"independent":[113],"each,":[116],"offering":[117],"precise":[118],"manipulation":[119],"avatar's":[123],"We":[128],"also":[129],"demonstrate":[130],"its":[131],"flexibility":[132],"in":[133,164],"integrating":[134],"with":[135],"methods,":[140],"bridging":[141],"gap":[143],"between":[144],"model-based":[146],"approaches":[147],"techniques.":[151],"Extensive":[152],"experiments":[153],"show":[154],"our":[156],"method":[157],"outperforms":[158],"recent":[159],"audio-driven":[160],"models":[163],"controllability.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}