{"id":"https://openalex.org/W7160889257","doi":"https://doi.org/10.48550/arxiv.2605.09956","title":"SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis","display_name":"SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160889257","doi":"https://doi.org/10.48550/arxiv.2605.09956"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09956","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.09956","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135956914","display_name":"Peng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135981968","display_name":"Zhen Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135933863","display_name":"Jia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135952121","display_name":"Xueliang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xueliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135921881","display_name":"Zhenzhen Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhenzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135989820","display_name":"Lingyun Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Lingyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.6010000109672546,"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":0.6010000109672546,"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":0.36629998683929443,"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/T11322","display_name":"Facial Rejuvenation and Surgery Techniques","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/2708","display_name":"Dermatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.8223999738693237},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4936999976634979},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46070000529289246},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46059998869895935},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.42829999327659607},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42149999737739563},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4180000126361847},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.415800005197525},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4059000015258789}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8223999738693237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505999803543091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6837000250816345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5889000296592712},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.415800005197525},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2777708103","wikidata":"https://www.wikidata.org/wiki/Q852589","display_name":"Motion blur","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09956","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.09956","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09956","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-quality,":[0],"real-time":[1],"talking":[2],"head":[3,84],"synthesis":[4],"remains":[5],"a":[6,32,55,87,96],"fundamental":[7],"challenge":[8],"in":[9,120],"computer":[10],"vision.":[11],"Existing":[12],"reconstruction-":[13],"and":[14,72,79,103,110,124],"rendering-based":[15],"methods":[16,119],"typically":[17],"rely":[18],"on":[19],"identity-specific":[20],"models,":[21],"limiting":[22],"cross-identity":[23],"generalization.":[24],"To":[25],"address":[26],"this":[27],"issue,":[28],"we":[29,63,94],"propose":[30],"SDTalk,":[31],"one-shot":[33],"3D":[34],"Gaussian":[35],"Splatting":[36],"(3DGS)-based":[37],"framework":[38,50],"that":[39,115],"generalizes":[40],"to":[41,100],"unseen":[42],"identities":[43],"without":[44],"personalized":[45],"training":[46,57],"or":[47],"fine-tuning.":[48],"Our":[49],"comprises":[51],"two":[52],"modules":[53],"with":[54],"two-stage":[56],"strategy.":[58],"In":[59,90],"the":[60,69,91],"first":[61],"stage,":[62,93],"incorporate":[64],"structured":[65],"facial":[66,105],"priors":[67],"into":[68],"reconstruction":[70,85],"module":[71],"separately":[73],"predict":[74],"3DGS":[75],"parameters":[76],"for":[77],"visible":[78],"occluded":[80],"regions,":[81],"enabling":[82],"complete":[83],"from":[86],"single":[88],"image.":[89],"second":[92],"introduce":[95],"dual-branch":[97],"motion":[98],"field":[99],"model":[101],"coarse":[102],"fine":[104],"dynamics,":[106],"improving":[107],"detail":[108],"fidelity":[109],"lip":[111],"synchronization.":[112],"Experiments":[113],"demonstrate":[114],"SDTalk":[116],"surpasses":[117],"existing":[118],"both":[121],"visual":[122],"quality":[123],"inference":[125],"efficiency.":[126]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}