{"id":"https://openalex.org/W4408355799","doi":"https://doi.org/10.1109/icassp49660.2025.10888438","title":"KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation","display_name":"KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355799","doi":"https://doi.org/10.1109/icassp49660.2025.10888438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5005164015","display_name":"Guanwen Feng","orcid":"https://orcid.org/0000-0002-1190-676X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanwen Feng","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109785897","display_name":"Siyu Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Jin","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Qian","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044422446","display_name":"Yunan Li","orcid":"https://orcid.org/0000-0001-7316-4354"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunan Li","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007404362","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0002-2872-388X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Computer Science and Technology,Xi&#x2019;an,China,710071","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005164015"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75808763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9890999794006348,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9865000247955322,"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/T12290","display_name":"Human Motion and Animation","score":0.957099974155426,"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/sync","display_name":"sync","score":0.7671935558319092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6997708082199097},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6448519825935364},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5981769561767578},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.42342495918273926},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34038862586021423},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1799660325050354},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10538089275360107},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07621431350708008}],"concepts":[{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.7671935558319092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997708082199097},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6448519825935364},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5981769561767578},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42342495918273926},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34038862586021423},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1799660325050354},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10538089275360107},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07621431350708008},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323230","display_name":"Xidian University","ror":"https://ror.org/05s92vm98"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2004797340","https://openalex.org/W2062222051","https://openalex.org/W2107037917","https://openalex.org/W2107699930","https://openalex.org/W2766585573","https://openalex.org/W2962785568","https://openalex.org/W2978956737","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3127995079","https://openalex.org/W3180794345","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200631136","https://openalex.org/W4221151978","https://openalex.org/W4386066256","https://openalex.org/W4390872116","https://openalex.org/W4390872742","https://openalex.org/W4400034442","https://openalex.org/W4402716255","https://openalex.org/W4402726971","https://openalex.org/W4402915563","https://openalex.org/W4411049949","https://openalex.org/W6757817989","https://openalex.org/W6765779288","https://openalex.org/W6849049266","https://openalex.org/W6851732043","https://openalex.org/W6861881666","https://openalex.org/W6866597880","https://openalex.org/W6867176674","https://openalex.org/W6869437045","https://openalex.org/W6870177550","https://openalex.org/W6873845366"],"related_works":["https://openalex.org/W4392306433","https://openalex.org/W2524993630","https://openalex.org/W2063547430","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1878822803","https://openalex.org/W1995263003","https://openalex.org/W2222580448"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress":[2],"in":[3,130],"NeRF-based":[4],"talking":[5,126],"head":[6,127],"generation,":[7],"problems":[8],"like":[9],"poor":[10],"lip":[11,53,69],"synchronization":[12],"and":[13,43,71,102,119],"inefficient":[14],"resource":[15,113],"usage":[16],"remain.":[17],"To":[18],"solve":[19],"these,":[20],"we":[21,29,82],"propose":[22],"KANFace,":[23],"a":[24,31,93],"lightweight":[25],"framework.":[26],"In":[27],"preprocessing,":[28],"introduce":[30,83],"Lip-Sync":[32],"Enhancement":[33],"Module":[34],"that":[35],"uses":[36],"Wav2Lip":[37],"to":[38,46,77,85,89,99],"extract":[39],"high-resolution":[40],"audio":[41],"features":[42,63,70],"map":[44,86],"them":[45],"an":[47],"explicit":[48],"intermediate":[49],"representation,":[50],"ensuring":[51],"precise":[52],"movement":[54],"alignment":[55],"with":[56,66],"the":[57,74],"speaker\u2019s":[58],"identity.":[59],"These":[60],"predicted":[61],"lip-sync":[62,117],"are":[64],"combined":[65],"fundamental":[67],"audio-extracted":[68],"injected":[72],"into":[73],"rendering":[75],"module":[76],"improve":[78],"synchronization.":[79],"For":[80],"rendering,":[81],"FastKAN":[84],"spatial":[87],"points":[88],"color":[90,108],"values.":[91],"As":[92],"variant":[94],"of":[95],"KAN,":[96],"FastKAN\u2019s":[97],"sensitivity":[98],"3D":[100],"scenes":[101],"efficient":[103],"structure":[104],"enable":[105],"precise,":[106],"fast":[107],"prediction.":[109],"Our":[110],"framework":[111],"reduces":[112],"consumption":[114],"while":[115],"enhancing":[116],"accuracy":[118],"facial":[120],"reconstruction,":[121],"making":[122],"it":[123],"ideal":[124],"for":[125],"generation":[128],"tasks":[129],"resource-limited":[131],"settings.":[132],"Project:":[133],"https://peterfanfan.github.io/KAN-Face/":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
