{"id":"https://openalex.org/W4408354800","doi":"https://doi.org/10.1109/icassp49660.2025.10889648","title":"Gaussian-Face: Talking Head Generation with Hybrid Density via 3D Gaussian Splatting","display_name":"Gaussian-Face: Talking Head Generation with Hybrid Density via 3D Gaussian Splatting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354800","doi":"https://doi.org/10.1109/icassp49660.2025.10889648"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5109552527","display_name":"Guanwen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanwen Feng","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi’an,China,710071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi’an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758235","display_name":"Yilin Zhang","orcid":"https://orcid.org/0000-0002-7059-2553"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Zhang","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi’an,China,710071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi’an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044422446","display_name":"Yunan Li","orcid":"https://orcid.org/0000-0001-7316-4354"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunan Li","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi’an,China,710071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi’an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027385708","display_name":"Siyu Jin","orcid":"https://orcid.org/0000-0001-5260-041X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Jin","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi’an,China,710071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi’an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007404362","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0002-2872-388X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi’an,China,710071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi’an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9811999797821045,"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/T11448","display_name":"Face recognition and analysis","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7089496850967407},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6388343572616577},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5327012538909912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48069554567337036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4010290503501892},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08493542671203613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089496850967407},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6388343572616577},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5327012538909912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48069554567337036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4010290503501892},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08493542671203613},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320334111","display_name":"Innovation Fund","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2769666294","https://openalex.org/W2962785568","https://openalex.org/W3011070051","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3109585842","https://openalex.org/W3136656704","https://openalex.org/W3192148059","https://openalex.org/W3203570626","https://openalex.org/W3211147706","https://openalex.org/W3215589927","https://openalex.org/W4212935216","https://openalex.org/W4221151978","https://openalex.org/W4232452729","https://openalex.org/W4249736682","https://openalex.org/W4310379947","https://openalex.org/W4312233178","https://openalex.org/W4312234520","https://openalex.org/W4312253380","https://openalex.org/W4312301053","https://openalex.org/W4312325284","https://openalex.org/W4312326867","https://openalex.org/W4312607553","https://openalex.org/W4312925709","https://openalex.org/W4385318467","https://openalex.org/W4390872116","https://openalex.org/W4395443867","https://openalex.org/W4395686506","https://openalex.org/W4411049949","https://openalex.org/W6679669933","https://openalex.org/W6766978945","https://openalex.org/W6781421651","https://openalex.org/W6781568228","https://openalex.org/W6839556448","https://openalex.org/W6861881666","https://openalex.org/W6873845366"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"audio-driven":[3,61],"neural":[4],"radiance":[5],"field":[6],"(NeRF)-based":[7],"talking":[8],"head":[9],"generation":[10],"techniques":[11],"have":[12,20],"achieved":[13],"impressive":[14],"results.":[15],"However,":[16],"these":[17],"methods":[18],"still":[19],"some":[21],"limitations,":[22],"such":[23],"as":[24],"unsynchronized":[25],"lip":[26,112],"movements":[27],"and":[28,50,73,100,130],"visual":[29],"jitter.":[30],"Recently,":[31],"3D":[32,42,95,111],"Gaussian":[33,43],"splatting":[34],"has":[35],"gradually":[36],"replaced":[37],"NeRF.":[38],"Compared":[39],"to":[40,92,107,110,135],"NeRF,":[41],"offers":[44],"notable":[45],"advantages,":[46],"including":[47],"higher":[48],"efficiency":[49],"better":[51],"reconstruction":[52],"quality.":[53],"Based":[54],"on":[55],"this,":[56,87],"we":[57,88,119],"propose":[58,120],"Gaussian-Face,":[59],"an":[60],"Gaussian-based":[62],"facial":[63,78,117,138],"avatar.":[64],"With":[65],"just":[66],"a":[67,75,103,121],"few":[68],"minutes":[69],"of":[70,97],"monocular":[71],"video":[72],"audio,":[74],"high-fidelity,":[76],"driveable":[77],"avatar":[79],"can":[80],"be":[81],"reconstructed":[82],"within":[83],"hours.":[84],"To":[85,114],"achieve":[86],"first":[89],"use":[90],"FLAME":[91],"obtain":[93],"the":[94,98],"representation":[96],"face":[99],"then":[101],"design":[102],"Lip":[104],"Motion":[105],"Translator":[106],"map":[108],"audio":[109],"representations.":[113],"model":[115],"higher-quality":[116],"details,":[118],"hybrid":[122],"density":[123],"modeling":[124],"method":[125],"that":[126],"balances":[127],"rendering":[128],"speed":[129],"quality,":[131],"enabling":[132],"our":[133],"approach":[134],"render":[136],"high-fidelity":[137],"avatars":[139],"at":[140],"more":[141],"than":[142],"160":[143],"FPS.":[144],"Project":[145],"page:":[146],"https://peterfanfan.github.io/Gaussian-Face/":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}