{"id":"https://openalex.org/W4395065528","doi":"https://doi.org/10.1145/3664647.3681675","title":"GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting","display_name":"GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4395065528","doi":"https://doi.org/10.1145/3664647.3681675"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.14037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054231785","display_name":"Hongyun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyun Yu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-2426-1014","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhan Qu","orcid":"https://orcid.org/0009-0009-5570-0884"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Qu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-5570-0884","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qihang Yu","orcid":"https://orcid.org/0009-0000-2650-5080"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Yu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-2650-5080","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064448826","display_name":"Jianchuan Chen","orcid":"https://orcid.org/0000-0001-5784-0965"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchuan Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5784-0965","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhonghua Jiang","orcid":"https://orcid.org/0000-0002-6782-830X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghua Jiang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6782-830X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwen Chen","orcid":"https://orcid.org/0000-0002-8302-8839"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwen Chen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8302-8839","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-0030-8289"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang University &amp; Shanghai Institute for Advanced Study, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0030-8289","affiliations":[{"raw_affiliation_string":"Zhejiang University &amp; Shanghai Institute for Advanced Study, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113934524","display_name":"Jimin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimin Xu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-8932-066X","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-8807","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020976131","display_name":"Chengfei Lv","orcid":"https://orcid.org/0009-0000-4918-7425"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengfei Lv","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-4918-7425","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gang Yu","orcid":"https://orcid.org/0009-0001-1185-1244"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-1185-1244","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5527,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95810845,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3548","last_page":"3557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9812999963760376,"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":0.9812999963760376,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9607999920845032,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9373000264167786,"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/computer-science","display_name":"Computer science","score":0.7105594873428345},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5863903164863586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4336179196834564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38018932938575745},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33071160316467285},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08461755514144897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105594873428345},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5863903164863586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4336179196834564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38018932938575745},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33071160316467285},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08461755514144897},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681675","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.14037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14037","pdf_url":"https://arxiv.org/pdf/2404.14037","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.14037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.14037","pdf_url":"https://arxiv.org/pdf/2404.14037","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395065528.pdf","grobid_xml":"https://content.openalex.org/works/W4395065528.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2017107803","https://openalex.org/W2107037917","https://openalex.org/W2295628903","https://openalex.org/W2295661697","https://openalex.org/W2739192055","https://openalex.org/W2769666294","https://openalex.org/W2884460600","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2979894294","https://openalex.org/W3006295631","https://openalex.org/W3006410788","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3109317096","https://openalex.org/W3109585842","https://openalex.org/W3153220274","https://openalex.org/W3154411171","https://openalex.org/W3182714435","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4212935216","https://openalex.org/W4214731463","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4313130906","https://openalex.org/W4321020813","https://openalex.org/W4375869161","https://openalex.org/W4382240211","https://openalex.org/W4385318467","https://openalex.org/W4385483513","https://openalex.org/W4385490328","https://openalex.org/W4386066256","https://openalex.org/W4387967971"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4395014643","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Recent":[0],"works":[1],"on":[2,62,174,191],"audio-driven":[3,57],"talking":[4,58,155],"head":[5,59,156],"synthesis":[6,60],"using":[7],"Neural":[8],"Radiance":[9],"Fields":[10],"(NeRF)":[11],"have":[12,32],"achieved":[13,81],"impressive":[14],"results.":[15],"However,":[16],"due":[17],"to":[18,85,109,129],"inadequate":[19],"pose":[20],"and":[21,42,45,97,118,140,162,186],"expression":[22],"control":[23,75],"caused":[24],"by":[25,82],"NeRF":[26],"implicit":[27],"representation,":[28],"these":[29],"methods":[30,153],"still":[31],"some":[33],"limitations,":[34],"such":[35],"as":[36],"unsynchronized":[37],"or":[38],"unnatural":[39],"lip":[40,106,120,160],"movements,":[41],"visual":[43,164],"jitter":[44],"artifacts.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"GaussianTalker,":[52],"a":[53,135],"novel":[54],"method":[55,167],"for":[56,182],"based":[61],"3D":[63,72,86],"Gaussian":[64,99,124],"Splatting.":[65],"With":[66],"the":[67,77,110,180],"explicit":[68],"representation":[69,133],"property":[70],"of":[71,76,91,171],"Gaussians,":[73],"intuitive":[74],"facial":[78,87,131],"motion":[79,121],"is":[80],"binding":[83],"Gaussians":[84],"models.":[88],"GaussianTalker":[89,149],"consists":[90],"two":[92],"modules,":[93],"Speaker-specific":[94,101,127],"Motion":[95,102],"Translator":[96,103],"Dynamic":[98,123],"Renderer.":[100],"achieves":[104,168],"accurate":[105],"movements":[107],"specific":[108],"target":[111],"speaker":[112],"through":[113],"universalized":[114],"audio":[115],"feature":[116],"extraction":[117],"customized":[119],"generation.":[122],"Renderer":[125],"introduces":[126],"BlendShapes":[128],"enhance":[130],"detail":[132],"via":[134],"latent":[136],"pose,":[137],"delivering":[138,158],"stable":[139],"realistic":[141],"rendered":[142],"videos.":[143],"Extensive":[144],"experimental":[145],"results":[146],"suggest":[147],"that":[148],"outperforms":[150],"existing":[151],"state-of-the-art":[152],"in":[154],"synthesis,":[157],"precise":[159],"synchronization":[161],"exceptional":[163],"quality.":[165],"Our":[166],"rendering":[169,184],"speeds":[170],"130":[172],"FPS":[173],"NVIDIA":[175],"RTX4090":[176],"GPU,":[177],"significantly":[178],"exceeding":[179],"threshold":[181],"real-time":[183],"performance,":[185],"can":[187],"potentially":[188],"be":[189],"deployed":[190],"other":[192],"hardware":[193],"platforms.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
