{"id":"https://openalex.org/W7140369046","doi":"https://doi.org/10.1109/tip.2026.3676251","title":"High-Fidelity and Lip-Synced Talking Face Synthesis via Landmark-Based Diffusion Model","display_name":"High-Fidelity and Lip-Synced Talking Face Synthesis via Landmark-Based Diffusion Model","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140369046","doi":"https://doi.org/10.1109/tip.2026.3676251","pmid":"https://pubmed.ncbi.nlm.nih.gov/41886322"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3676251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3676251","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":null,"display_name":"Weizhi Zhong","orcid":"https://orcid.org/0000-0003-2402-4691"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weizhi Zhong","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2402-4691","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130651556","display_name":"Junfan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfan Lin","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8717-8351","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098301","display_name":"Peixin Chen","orcid":"https://orcid.org/0000-0003-1308-8016"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peixin Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130684292","display_name":"Feng Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Gao","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1843-3180","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130633308","display_name":"Liang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130632378","display_name":"Guanbin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4805-0926","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63300478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"3369","last_page":"3380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8927000164985657,"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":0.8927000164985657,"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":0.042500000447034836,"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":0.02979999966919422,"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/face","display_name":"Face (sociological concept)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.38659998774528503},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3368000090122223},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3273000121116638},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3176000118255615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29739999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5339000225067139},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.289000004529953},{"id":"https://openalex.org/C2984999661","wikidata":"https://www.wikidata.org/wiki/Q603159","display_name":"Surface fitting","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2508000135421753}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000033","qualifier_name":"anatomy & histology","is_major_topic":true},{"descriptor_ui":"D005145","descriptor_name":"Face","qualifier_ui":"Q000033","qualifier_name":"anatomy & histology","is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D008046","descriptor_name":"Lip","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D008046","descriptor_name":"Lip","qualifier_ui":"Q000000981","qualifier_name":"diagnostic imaging","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3676251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3676251","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:41886322","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41886322","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/G1437690383","display_name":null,"funder_award_id":"2024YFB3908503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3315468253","display_name":null,"funder_award_id":"62506180","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4751043524","display_name":null,"funder_award_id":"62322608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G47991194","display_name":null,"funder_award_id":"2025M771522","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,107,201],"face":[2,108,202],"video":[3],"generation":[4],"has":[5],"attracted":[6],"increasing":[7],"attention":[8],"due":[9,70],"to":[10,26,42,71,88,131,147,175],"its":[11],"huge":[12],"industrial":[13],"potential.":[14],"Some":[15],"previous":[16,80],"methods":[17,81],"focus":[18],"on":[19,83],"learning":[20],"a":[21,101],"direct":[22],"mapping":[23,39,128],"from":[24,67,129,209],"audio":[25,130],"visual":[27],"content.":[28],"Despite":[29],"progress,":[30],"they":[31],"often":[32],"struggle":[33],"with":[34,152,181],"the":[35,38,62,72,125,149,153,177,182,210],"ambiguity":[36],"of":[37,75,134],"process,":[40],"leading":[41],"flawed":[43],"results.":[44],"An":[45],"alternative":[46],"strategy":[47],"involves":[48],"facial":[49,53,112],"structural":[50],"representations":[51,116],"(e.g.,":[52],"landmarks)":[54],"as":[55,114],"intermediaries.":[56],"This":[57],"multi-stage":[58],"approach":[59,195],"better":[60],"preserves":[61],"appearance":[63,188,207],"details":[64,208],"but":[65],"suffers":[66],"error":[68],"accumulation":[69],"independent":[73],"optimization":[74,164],"different":[76],"stages.":[77],"Moreover,":[78],"most":[79],"rely":[82],"generative":[84],"adversarial":[85],"networks,":[86],"prone":[87],"training":[89],"instability":[90],"and":[91,136,199],"mode":[92],"collapse.":[93],"To":[94],"address":[95],"these":[96],"challenges,":[97],"our":[98,194],"study":[99],"proposes":[100],"novel":[102],"landmark-based":[103],"diffusion":[104],"model":[105],"for":[106,165,185],"generation,":[109],"which":[110,161],"leverages":[111],"landmarks":[113,157],"intermediate":[115],"while":[117],"enabling":[118],"end-to-end":[119,163],"optimization.":[120],"Specifically,":[121],"we":[122,139],"first":[123],"establish":[124],"less":[126],"ambiguous":[127],"landmark":[132],"motion":[133,151,154,184],"lip":[135,167],"jaw.":[137],"Then,":[138],"introduce":[140],"an":[141],"innovative":[142],"conditioning":[143],"module":[144],"called":[145],"TalkFormer":[146,170],"align":[148,176],"synthesized":[150],"represented":[155],"by":[156],"via":[158],"differentiable":[159],"cross-attention,":[160],"enables":[162],"improved":[166],"synchronization.":[168],"Besides,":[169],"employs":[171],"implicit":[172],"feature":[173],"warping":[174],"reference":[178,211],"image":[179],"features":[180],"target":[183],"preserving":[186,204],"more":[187,205],"details.":[189],"Extensive":[190],"experiments":[191],"demonstrate":[192],"that":[193],"can":[196],"synthesize":[197],"high-fidelity":[198],"lip-synced":[200],"videos,":[203],"subject":[206],"image.":[212]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2026-03-27T00:00:00"}