{"id":"https://openalex.org/W7163138398","doi":"https://doi.org/10.1109/tip.2026.3697655","title":"HP-Gaussian: Head Prior-Guided Gaussian Splatting for Personalized Talking Head Synthesis From Few-Second Video","display_name":"HP-Gaussian: Head Prior-Guided Gaussian Splatting for Personalized Talking Head Synthesis From Few-Second Video","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163138398","doi":"https://doi.org/10.1109/tip.2026.3697655","pmid":"https://pubmed.ncbi.nlm.nih.gov/42228662"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3697655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697655","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101834459","display_name":"Shuai Shen","orcid":"https://orcid.org/0009-0005-9051-1107"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Shen","raw_affiliation_strings":["School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9051-1107","affiliations":[{"raw_affiliation_string":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082419115","display_name":"Wanhua Li","orcid":"https://orcid.org/0000-0002-2730-0543"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wanhua Li","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2730-0543","affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137645899","display_name":"Yunpeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunpeng Zhang","raw_affiliation_strings":["PhiGent Robotics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PhiGent Robotics, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831163","display_name":"Weipeng Hu","orcid":"https://orcid.org/0000-0003-2886-7346"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weipeng Hu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460385","display_name":"Jiwen Lu","orcid":"https://orcid.org/0000-0002-6121-5529"},"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":"Jiwen Lu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology (BNRist) and the Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6121-5529","affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology (BNRist) and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137701004","display_name":"Yap-Peng Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Yap-Peng Tan","raw_affiliation_strings":["VinUniversity, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-0645-9109","affiliations":[{"raw_affiliation_string":"VinUniversity, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"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":0.69419519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"5880","last_page":"5893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8831999897956848,"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":0.8831999897956848,"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":0.05950000137090683,"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":0.010400000028312206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.37459999322891235},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3684999942779541},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3359000086784363},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31349998712539673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2800000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003000020980835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6499000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413000226020813},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3697655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3697655","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42228662","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42228662","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3510215249","display_name":null,"funder_award_id":"62125603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7641150618","display_name":null,"funder_award_id":"62441616","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8443129088","display_name":null,"funder_award_id":"62336004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Gaussian":[0,31,53,60,96,103],"Splatting-based":[1],"talking":[2,35,129,165,179,195],"head":[3,36,83,150,196],"synthesis":[4,37,126],"has":[5],"made":[6],"significant":[7],"progress":[8],"in":[9,124,194],"recent":[10],"years,":[11],"yet":[12],"existing":[13],"methods":[14],"often":[15],"struggle":[16],"with":[17,45,181],"generalization":[18],"beyond":[19],"specific":[20],"training":[21,48,133,184],"identity.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,99,154],"propose":[27],"Head":[28],"Prior":[29],"guided":[30],"Splatting":[32,54],"for":[33,161,190,207],"personalized":[34,121,158,178],"(HP-Gaussian)":[38],"that":[39,105,171],"can":[40,174],"generalize":[41],"to":[42,80,146],"new":[43,188],"identities":[44,75,145],"only":[46],"few":[47,183],"data.":[49],"Unlike":[50],"traditional":[51],"optimization-based":[52],"methods,":[55],"our":[56,172,202],"approach":[57],"directly":[58],"predicts":[59],"parameters":[61],"from":[62,85],"multi-modal":[63],"inputs,":[64],"including":[65],"audio":[66],"and":[67,177,192,211],"visual":[68,209],"cues.":[69],"This":[70],"feed-forward":[71],"design":[72],"enables":[73],"multiple":[74],"pre-training,":[76],"allowing":[77],"the":[78,117,125,148,156],"model":[79,139],"learn":[81],"shared":[82],"priors":[84],"large-scale":[86],"datasets,":[87],"while":[88],"supporting":[89],"flexible":[90],"speaker-specific":[91],"adaptation.":[92],"To":[93],"further":[94],"enhance":[95],"feature":[97],"learning,":[98],"introduce":[100,155],"a":[101,131,187],"Spatial":[102],"Transformer":[104],"captures":[106],"correlations":[107],"among":[108],"neighboring":[109],"Gaussians,":[110],"improving":[111],"parameter":[112],"estimation":[113],"accuracy.":[114],"Additionally,":[115],"recognizing":[116],"critical":[118],"importance":[119],"of":[120,127],"speaking":[122],"styles":[123],"high-quality":[128],"videos,":[130],"two-stage":[132],"strategy":[134],"is":[135,140],"implemented.":[136],"A":[137],"base":[138],"initially":[141],"trained":[142],"across":[143],"diverse":[144],"establish":[147],"foundational":[149],"prior":[151],"knowledge.":[152],"Subsequently,":[153],"short-video":[157],"adaptation":[159],"phase":[160],"more":[162],"realistic":[163],"customized":[164],"video":[166,204],"generation.":[167],"Extensive":[168],"experiments":[169],"demonstrate":[170],"HP-Gaussian":[173],"synthesize":[175],"high-fidelity":[176],"videos":[180],"remarkably":[182],"examples,":[185],"setting":[186],"benchmark":[189],"efficiency":[191],"quality":[193],"synthesis.":[197],"We":[198],"highly":[199],"recommend":[200],"viewing":[201],"demonstration":[203],"at":[205],"https://youtu.be/RpjWdvikKhU":[206],"intuitive":[208],"comparisons":[210],"qualitative":[212],"results.":[213]},"counts_by_year":[],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-06-03T00:00:00"}