{"id":"https://openalex.org/W4386133969","doi":"https://doi.org/10.1109/tmm.2023.3308441","title":"SD-NeRF: Towards Lifelike Talking Head Animation via Spatially-Adaptive Dual-Driven NeRFs","display_name":"SD-NeRF: Towards Lifelike Talking Head Animation via Spatially-Adaptive Dual-Driven NeRFs","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386133969","doi":"https://doi.org/10.1109/tmm.2023.3308441"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3308441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3308441","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5101834459","display_name":"Shuai Shen","orcid":"https://orcid.org/0009-0005-9051-1107"},"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":true,"raw_author_name":"Shuai Shen","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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/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":"Wanhua Li","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770401","display_name":"Xiaoke Huang","orcid":"https://orcid.org/0000-0003-1658-6432"},"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":"Xiaoke Huang","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705530","display_name":"Zheng Zhu","orcid":"https://orcid.org/0000-0002-4435-1692"},"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":"Zheng Zhu","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"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":"Jie Zhou","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","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":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101834459"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.3701,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9406711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"3221","last_page":"3234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9980000257492065,"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":0.9896000027656555,"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/computer-science","display_name":"Computer science","score":0.8461753129959106},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.730624794960022},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6188802719116211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6099024415016174},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5355182886123657},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5336397886276245},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.5081605911254883},{"id":"https://openalex.org/keywords/human-head","display_name":"Human head","score":0.4659394323825836},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4605587422847748},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4463620185852051},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.43974146246910095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40056273341178894},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.25767260789871216},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12953051924705505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461753129959106},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.730624794960022},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6188802719116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6099024415016174},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5355182886123657},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5336397886276245},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.5081605911254883},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.4659394323825836},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4605587422847748},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4463620185852051},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.43974146246910095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40056273341178894},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25767260789871216},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12953051924705505},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C125287762","wikidata":"https://www.wikidata.org/wiki/Q1758948","display_name":"Absorption (acoustics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3308441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3308441","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"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"}],"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":74,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2237250383","https://openalex.org/W2301937176","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2752782242","https://openalex.org/W2944294033","https://openalex.org/W2960274051","https://openalex.org/W2962785568","https://openalex.org/W2981263323","https://openalex.org/W2990452356","https://openalex.org/W3019952993","https://openalex.org/W3021282624","https://openalex.org/W3021962567","https://openalex.org/W3025503473","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3097792222","https://openalex.org/W3099505600","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3109908659","https://openalex.org/W3112734613","https://openalex.org/W3114462840","https://openalex.org/W3118548710","https://openalex.org/W3119557339","https://openalex.org/W3121523901","https://openalex.org/W3135222947","https://openalex.org/W3153220274","https://openalex.org/W3172598908","https://openalex.org/W3173531806","https://openalex.org/W3174763799","https://openalex.org/W3177150198","https://openalex.org/W3180770160","https://openalex.org/W3180922390","https://openalex.org/W3182714435","https://openalex.org/W3186090335","https://openalex.org/W3186700381","https://openalex.org/W3187364420","https://openalex.org/W3188678927","https://openalex.org/W3195620846","https://openalex.org/W3197199219","https://openalex.org/W3200121240","https://openalex.org/W3202037070","https://openalex.org/W3211147706","https://openalex.org/W3214311327","https://openalex.org/W4200174933","https://openalex.org/W4210657261","https://openalex.org/W4214731463","https://openalex.org/W4226204502","https://openalex.org/W4309876056","https://openalex.org/W4312233178","https://openalex.org/W4312680644","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4385245566","https://openalex.org/W4386075487","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6640090968","https://openalex.org/W6737896281","https://openalex.org/W6755308174","https://openalex.org/W6780879210","https://openalex.org/W6811548253","https://openalex.org/W6838810623","https://openalex.org/W6847187194","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W2121378366","https://openalex.org/W2292270636","https://openalex.org/W3112102641","https://openalex.org/W2434467261","https://openalex.org/W2013184069","https://openalex.org/W2535923857","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W126583968","https://openalex.org/W2532377291"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"great":[4],"progress":[5],"in":[6,62],"audio-driven":[7],"talking":[8,70,112,126,191,242],"head":[9,25,71,113,192,243],"animation.":[10],"Among":[11],"these":[12,218],"methods,":[13],"the":[14,19,23,45,77,157,166,206],"3D-based":[15,37],"ones":[16],"better":[17],"preserve":[18],"3D":[20,40,78,98],"consistency":[21],"of":[22,205],"generated":[24],"and":[26,48,141,148,177,199,228],"produce":[27],"more":[28,189,240],"natural":[29,147],"results":[30,230],"compared":[31,245],"with":[32,222,233,246],"2D-based":[33],"approaches.":[34],"However,":[35],"most":[36],"methods":[38],"employ":[39],"morphable":[41],"face":[42],"models":[43],"as":[44,173,197],"intermediate":[46],"representation":[47],"involve":[49],"multi-stage":[50],"training,":[51],"which":[52,74,144,216],"may":[53],"lead":[54],"to":[55,92,165,184],"error":[56],"accumulation.":[57],"To":[58],"alleviate":[59],"this":[60,63,195],"problem,":[61],"article,":[64],"we":[65,116,169,209],"propose":[66,210],"a":[67,82,124,186,211,223],"fully":[68,122,154],"end-to-end":[69],"animation":[72],"method,":[73],"implicitly":[75],"grasps":[76],"structures":[79],"by":[80,156],"learning":[81],"conditional":[83],"Neural":[84],"Radiance":[85],"Field":[86],"(NeRF).":[87],"As":[88],"NeRF":[89,182,214],"has":[90],"proven":[91],"be":[93,153],"an":[94,179],"effective":[95],"tool":[96],"for":[97,111],"modeling,":[99],"one":[100],"can":[101],"learn":[102],"dynamic":[103],"neural":[104],"radiance":[105],"fields":[106],"conditioned":[107],"on":[108],"audio":[109,119,158,198],"signals":[110,120,159],"synthesis.":[114,193],"Furthermore,":[115],"argue":[117],"that":[118],"cannot":[121,152],"drive":[123],"lifelike":[125,190],"head.":[127],"When":[128],"people":[129],"are":[130,162],"talking,":[131],"they":[132,161],"usually":[133],"show":[134],"many":[135],"spontaneous":[136],"facial":[137,235],"movements":[138,151],"like":[139],"blinks":[140],"brow":[142],"movements,":[143],"makes":[145],"talkers":[146],"real.":[149],"These":[150],"driven":[155,220],"since":[160],"highly":[163],"unrelated":[164],"audio.":[167],"Therefore,":[168],"incorporate":[170],"motion":[171,200],"information":[172],"another":[174],"driving":[175],"factor":[176],"develop":[178],"audio-motion":[180],"dual-driven":[181],"model":[183],"take":[185],"step":[187],"toward":[188],"On":[194],"basis,":[196],"mainly":[201],"affect":[202],"different":[203],"regions":[204],"human":[207],"face,":[208],"Spatially-adaptive":[212],"Dual-driven":[213],"(SD-NeRF),":[215],"fuses":[217],"two":[219],"factors":[221],"spatially-adaptive":[224],"cross-attention":[225],"mechanism.":[226],"Quantitative":[227],"qualitative":[229],"demonstrate":[231],"that,":[232],"finer":[234],"controls,":[236],"our":[237],"method":[238],"produces":[239],"realistic":[241],"videos":[244],"existing":[247],"advanced":[248],"works.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
