{"id":"https://openalex.org/W4408345626","doi":"https://doi.org/10.1109/icassp49660.2025.10889463","title":"DFNeRF: Disentangled Facial Neural Radiance Fields for Text-based Editing of Free-view Talking Head","display_name":"DFNeRF: Disentangled Facial Neural Radiance Fields for Text-based Editing of Free-view Talking Head","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345626","doi":"https://doi.org/10.1109/icassp49660.2025.10889463"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889463","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":"conference-paper","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/A5113066134","display_name":"Benwang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Benwang Chen","raw_affiliation_strings":["Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449177","display_name":"Xiaoyu Li","orcid":"https://orcid.org/0000-0003-2588-1687"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China,518071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China,518071","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329006","display_name":"Xuan Wang","orcid":"https://orcid.org/0000-0002-6266-1387"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Wang","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China,518071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China,518071","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360395","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0235-1333"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China,518071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China,518071","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106404485","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0001-6317-8111"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Haoqian Wang","raw_affiliation_strings":["Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Shenzhen International Graduate School,Shenzhen,China,518071","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9976000189781189,"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":0.9976000189781189,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9584000110626221,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9298999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/radiance","display_name":"Radiance","score":0.7942163944244385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7398068308830261},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.7382124662399292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5171860456466675},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49948883056640625},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.42114633321762085},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4200742244720459},{"id":"https://openalex.org/keywords/hands-free","display_name":"Hands free","score":0.414673388004303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39257264137268066},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0906863808631897},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.07784914970397949}],"concepts":[{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.7942163944244385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398068308830261},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.7382124662399292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5171860456466675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49948883056640625},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.42114633321762085},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4200742244720459},{"id":"https://openalex.org/C3018339088","wikidata":"https://www.wikidata.org/wiki/Q28460","display_name":"Hands free","level":2,"score":0.414673388004303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39257264137268066},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0906863808631897},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.07784914970397949},{"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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889463","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":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1964202597","https://openalex.org/W2064076387","https://openalex.org/W2080072756","https://openalex.org/W2096733369","https://openalex.org/W2604379605","https://openalex.org/W2944294033","https://openalex.org/W2960274051","https://openalex.org/W2963081548","https://openalex.org/W3176721746","https://openalex.org/W3192148059","https://openalex.org/W3194357576","https://openalex.org/W3211147706","https://openalex.org/W4200382072","https://openalex.org/W4312955540","https://openalex.org/W4312990833","https://openalex.org/W4385490328","https://openalex.org/W4385682917","https://openalex.org/W4386066799","https://openalex.org/W4386075487","https://openalex.org/W4390872116","https://openalex.org/W4390872769","https://openalex.org/W4392903488","https://openalex.org/W4393148434","https://openalex.org/W4393248184","https://openalex.org/W4394597549","https://openalex.org/W4402955559","https://openalex.org/W4403081627","https://openalex.org/W4403792004","https://openalex.org/W4405382056","https://openalex.org/W4409262863","https://openalex.org/W6811548253","https://openalex.org/W6844194202","https://openalex.org/W6859110512","https://openalex.org/W6859319753","https://openalex.org/W6862876198","https://openalex.org/W6864518445","https://openalex.org/W6869123908","https://openalex.org/W6869873528","https://openalex.org/W6872435677","https://openalex.org/W6872441545","https://openalex.org/W6875631423","https://openalex.org/W6876568064"],"related_works":["https://openalex.org/W2896728493","https://openalex.org/W2392142157","https://openalex.org/W2043512367","https://openalex.org/W4321518006","https://openalex.org/W2331836163","https://openalex.org/W2024462231","https://openalex.org/W2005276308","https://openalex.org/W1994657804","https://openalex.org/W1970182911","https://openalex.org/W2347721387"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,84],"propose":[4],"a":[5,15,102,111,123],"text-based":[6],"approach":[7],"that":[8],"can":[9],"edit":[10],"the":[11,31,54,68,73,81,87,92,96,115,119,130,136],"speech":[12],"content":[13,94],"of":[14,25,126,138],"free-view":[16,74],"talking":[17,75],"head":[18,36,42,76],"based":[19,90],"on":[20,91],"its":[21],"transcript.":[22],"The":[23],"core":[24],"our":[26,139],"method":[27,99,109,140],"is":[28],"to":[29,61,100],"establish":[30],"relationship":[32],"between":[33,129],"phonemes":[34,117],"and":[35,44,121,143],"attributes.":[37],"To":[38],"avoid":[39],"discontinuities":[40],"in":[41,118],"pose":[43],"facial":[45,56],"expressions":[46],"caused":[47],"by":[48,67,78],"editing":[49],"mouth":[50,127],"shape.":[51],"We":[52],"design":[53],"disentangled":[55],"neural":[57],"radiance":[58],"fields":[59],"(DFNeRF)":[60],"automatically":[62],"disentangle":[63],"these":[64],"attributes":[65],"controlled":[66],"learned":[69],"latent":[70,88],"codes.":[71],"Using":[72],"synthesized":[77],"DFNeRF":[79],"as":[80],"base":[82],"corpus,":[83],"could":[85,113],"re-assemble":[86],"codes":[89],"new":[93],"using":[95],"phoneme":[97,107],"search":[98,108],"produce":[101],"seamless":[103],"edited":[104],"result.":[105],"Our":[106],"with":[110],"discriminator":[112],"find":[114],"best-matched":[116],"sequence":[120],"ensure":[122],"smooth":[124],"transition":[125],"shape":[128],"adjacent":[131],"phonemes.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"effectiveness":[137],"both":[141],"qualitatively":[142],"quantitatively.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}