{"id":"https://openalex.org/W7162523239","doi":"https://doi.org/10.1109/3dv69130.2026.00092","title":"From Blurry to Believable: Enhancing Low-Quality Talking Heads with 3D Generative Priors","display_name":"From Blurry to Believable: Enhancing Low-Quality Talking Heads with 3D Generative Priors","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7162523239","doi":"https://doi.org/10.1109/3dv69130.2026.00092"},"language":null,"primary_location":{"id":"doi:10.1109/3dv69130.2026.00092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"article","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/A5111024343","display_name":"Ding-Jiun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding-Jiun Huang","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704650","display_name":"Yuanhao Wang","orcid":"https://orcid.org/0009-0002-2737-4689"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanhao Wang","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065481040","display_name":"Shao-Ji Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shao-Ji Yuan","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125391100","display_name":"Albert Mosella-Montoro","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Mosella-Montoro","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047750700","display_name":"Francisco Vicente Carrasco","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francisco Vicente Carrasco","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137138080","display_name":"Cheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Texas A&#x0026;M University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&#x0026;M University,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108127869","display_name":"Fernando De la Torre","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando De la Torre","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.8532807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"915","last_page":"925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.3028999865055084,"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":0.3028999865055084,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.13609999418258667,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.11949999630451202,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5501000285148621},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33160001039505005},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3001999855041504},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2809999883174896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2685000002384186}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049000024795532},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5501000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5483999848365784},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24729999899864197},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24140000343322754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv69130.2026.00092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W2016462422","https://openalex.org/W2133665775","https://openalex.org/W2160126058","https://openalex.org/W2769666294","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W3035574324","https://openalex.org/W3108710777","https://openalex.org/W3139161477","https://openalex.org/W3173102319","https://openalex.org/W3182714435","https://openalex.org/W3211147706","https://openalex.org/W3215121054","https://openalex.org/W4210279013","https://openalex.org/W4221145744","https://openalex.org/W4225726688","https://openalex.org/W4231149888","https://openalex.org/W4286759403","https://openalex.org/W4312233178","https://openalex.org/W4312253380","https://openalex.org/W4312453532","https://openalex.org/W4312567281","https://openalex.org/W4312567873","https://openalex.org/W4312578889","https://openalex.org/W4312607553","https://openalex.org/W4312918802","https://openalex.org/W4319299838","https://openalex.org/W4372283500","https://openalex.org/W4385287058","https://openalex.org/W4385318467","https://openalex.org/W4386066152","https://openalex.org/W4386071565","https://openalex.org/W4386071566","https://openalex.org/W4386075534","https://openalex.org/W4386076143","https://openalex.org/W4386076259","https://openalex.org/W4386076320","https://openalex.org/W4386076478","https://openalex.org/W4390872731","https://openalex.org/W4394625634","https://openalex.org/W4399695991","https://openalex.org/W4400573499","https://openalex.org/W4402716022","https://openalex.org/W4402727530","https://openalex.org/W4402753521","https://openalex.org/W4402753958","https://openalex.org/W4403562099","https://openalex.org/W4403842335","https://openalex.org/W4404002621","https://openalex.org/W4404036125","https://openalex.org/W4404624502","https://openalex.org/W4409368439","https://openalex.org/W4412588014","https://openalex.org/W4413010757","https://openalex.org/W4413155801","https://openalex.org/W4413556514","https://openalex.org/W4415797248","https://openalex.org/W4415800701","https://openalex.org/W7103754474","https://openalex.org/W7133189404","https://openalex.org/W7133207707"],"related_works":[],"abstract_inverted_index":{"Creating":[0],"high-fidelity,":[1],"animatable":[2,40],"3D":[3,26,41,57,91,103,110,127],"talking":[4],"heads":[5],"is":[6,134,149],"crucial":[7],"for":[8,37,145],"immersive":[9],"applications,":[10],"yet":[11],"often":[12],"hindered":[13],"by":[14],"the":[15,98,116,120],"prevalence":[16],"of":[17,119,156],"low-quality":[18],"image":[19],"or":[20],"video":[21,72],"sources,":[22],"which":[23,133],"yield":[24],"poor":[25],"reconstructions.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"introduce":[32],"SuperHead,":[33],"a":[34,107,125,153],"novel":[35,108],"framework":[36],"enhancing":[38],"lowresolution,":[39],"head":[42,131,141],"avatars.":[43],"The":[44,147],"core":[45],"challenge":[46],"lies":[47],"in":[48,70,201],"synthesizing":[49],"high-quality":[50],"geometry":[51],"and":[52,58,63,73,161,170],"textures,":[53],"while":[54],"ensuring":[55],"both":[56],"temporal":[59],"consistency":[60],"during":[61],"animation":[62],"preserving":[64],"subject":[65],"identity.":[66],"Despite":[67],"recent":[68],"progress":[69],"image,":[71],"3D-based":[74],"superresolution":[75],"(<tex":[76],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77,82,178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$S":[78,83],"R$</tex>),":[79],"existing":[80],"<tex":[81,177],"R$</tex>":[84],"techniques":[85],"are":[86],"ill-equipped":[87],"to":[88,123,137,173],"handle":[89],"dynamic":[90,195],"inputs.":[92],"To":[93],"address":[94],"this,":[95],"SuperHead":[96,187],"leverages":[97],"rich":[99],"priors":[100],"from":[101,166],"pre-trained":[102],"generative":[104,121],"models":[105],"via":[106],"dynamics-aware":[109],"inversion":[111,148],"scheme.":[112],"This":[113],"process":[114],"optimizes":[115],"latent":[117],"representation":[118],"model":[122,142],"produce":[124],"super-resolved":[126],"Gaussian":[128],"Splatting":[129],"(3DGS)":[130],"model,":[132],"subsequently":[135],"rigged":[136],"an":[138],"underlying":[139],"parametric":[140],"(e.g.,":[143],"FLAME)":[144],"animation.":[146],"jointly":[150],"supervised":[151],"using":[152],"sparse":[154],"collection":[155],"upscaled":[157],"2D":[158],"face":[159],"renderings":[160],"corresponding":[162],"depth":[163],"maps,":[164],"captured":[165],"diverse":[167],"facial":[168,182,192],"expressions":[169],"camera":[171],"viewpoints,":[172],"ensure":[174],"realism":[175],"under":[176,194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$d":[179],"y$</tex>":[180],"namic":[181],"motions.":[183],"Experiments":[184],"demonstrate":[185],"that":[186],"generates":[188],"avatars":[189],"with":[190],"fine-grained":[191],"details":[193],"motions,":[196],"significantly":[197],"outperforming":[198],"baseline":[199],"methods":[200],"visual":[202],"quality.":[203]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}