{"id":"https://openalex.org/W4417297109","doi":"https://doi.org/10.1109/wacv61042.2026.00774","title":"GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting","display_name":"GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417297109","doi":"https://doi.org/10.1109/wacv61042.2026.00774"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.10939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110980495","display_name":"Madhav Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Madhav Agarwal","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020808232","display_name":"Ming\u2010Tian Zhang","orcid":"https://orcid.org/0000-0001-8808-9641"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mingtian Zhang","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076169111","display_name":"Laura Sevilla-Lara","orcid":"https://orcid.org/0000-0001-8276-0094"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laura Sevilla-Lara","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052824649","display_name":"Steven McDonagh","orcid":"https://orcid.org/0000-0001-7025-5197"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steven McDonagh","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02119857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8017","last_page":"8027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8357999920845032,"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":0.8357999920845032,"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":0.06539999693632126,"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":0.06419999897480011,"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/gaussian","display_name":"Gaussian","score":0.47699999809265137},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.43320000171661377},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.41370001435279846},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3855000138282776},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3384000062942505},{"id":"https://openalex.org/keywords/gaussian-network-model","display_name":"Gaussian network model","score":0.31850001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6689000129699707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6033999919891357},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.27799999713897705}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.10939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10939","pdf_url":"https://arxiv.org/pdf/2512.10939","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.10939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.10939","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.10939","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.10939","pdf_url":"https://arxiv.org/pdf/2512.10939","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Speech-driven":[0],"talking":[1,112],"heads":[2],"have":[3],"recently":[4],"emerged":[5],"and":[6,58,101,120],"enable":[7],"interactive":[8],"avatars.":[9,83],"However,":[10],"real-world":[11],"applications":[12],"are":[13,43,62],"limited,":[14],"as":[15],"current":[16],"methods":[17,30],"achieve":[18],"high":[19],"visual":[20],"fidelity":[21],"but":[22],"slow":[23],"or":[24,50],"fast":[25],"yet":[26,35,45],"temporally":[27],"unstable.":[28],"Diffusion":[29],"provide":[31],"realistic":[32,65],"image":[33],"generation,":[34],"struggle":[36],"with":[37],"one-shot":[38],"settings.":[39],"Gaussian":[40,52,74],"Splatting":[41,75],"approaches":[42],"real-time,":[44],"inaccuracies":[46],"in":[47],"facial":[48],"tracking,":[49],"inconsistent":[51],"mappings,":[53],"lead":[54],"to":[55,64,80,94],"unstable":[56],"outputs":[57],"video":[59,100],"artifacts":[60],"that":[61],"detrimental":[63],"use":[66],"cases.":[67],"We":[68,84],"address":[69],"this":[70],"problem":[71],"by":[72],"mapping":[73],"using":[76],"3D":[77],"Morphable":[78],"Models":[79],"generate":[81],"person-specific":[82],"introduce":[85],"transformer-based":[86],"prediction":[87],"of":[88,110],"model":[89],"parameters,":[90],"directly":[91],"from":[92],"audio,":[93],"drive":[95],"temporal":[96],"consistency.":[97],"From":[98],"monocular":[99],"independent":[102],"audio":[103],"speech":[104],"inputs,":[105],"our":[106],"method":[107],"enables":[108],"generation":[109],"real-time":[111],"head":[113],"videos":[114],"where":[115],"we":[116],"report":[117],"competitive":[118],"quantitative":[119],"qualitative":[121],"performance.":[122]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-12-13T00:00:00"}