{"id":"https://openalex.org/W4408352815","doi":"https://doi.org/10.1109/icassp49660.2025.10887890","title":"Realistic Real-Time Talking Head Synthesis with Grid Encoding and Progressive Conditioning","display_name":"Realistic Real-Time Talking Head Synthesis with Grid Encoding and Progressive Conditioning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352815","doi":"https://doi.org/10.1109/icassp49660.2025.10887890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887890","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/A5079284284","display_name":"Zhiling Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiling Ye","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd.,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd.,Chengdu,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102591438","display_name":"Liang-Guo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang-Guo Zhang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037049248","display_name":"Dingheng Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingheng Zeng","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104212958","display_name":"Quan L\u00fc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Lu","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101654008","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-4549-6372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd.,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T13382","display_name":"Robotics and Automated Systems","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9919999837875366,"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":0.9782999753952026,"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/encoding","display_name":"Encoding (memory)","score":0.7305397987365723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6571672558784485},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6447138786315918},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5801084041595459},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.49327796697616577},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36660945415496826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2544058561325073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07557255029678345}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7305397987365723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571672558784485},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6447138786315918},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5801084041595459},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.49327796697616577},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36660945415496826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2544058561325073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07557255029678345},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887890","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2603777577","https://openalex.org/W2604379605","https://openalex.org/W2738406145","https://openalex.org/W2745771616","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2981263323","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3107666850","https://openalex.org/W3109585842","https://openalex.org/W3159279967","https://openalex.org/W3174763799","https://openalex.org/W3177583232","https://openalex.org/W3182714435","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3192072773","https://openalex.org/W3207849023","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4200382072","https://openalex.org/W4210657261","https://openalex.org/W4221151978","https://openalex.org/W4312959196","https://openalex.org/W4321020813","https://openalex.org/W4385483513","https://openalex.org/W4386066812","https://openalex.org/W4386071653","https://openalex.org/W4386180266","https://openalex.org/W4390872116","https://openalex.org/W4390872696","https://openalex.org/W4404586213","https://openalex.org/W4411049949","https://openalex.org/W6774285787","https://openalex.org/W6851732043"],"related_works":["https://openalex.org/W2344176346","https://openalex.org/W2052307325","https://openalex.org/W1489675464","https://openalex.org/W1881653995","https://openalex.org/W2365635896","https://openalex.org/W2062287200","https://openalex.org/W2004526709","https://openalex.org/W2063101141","https://openalex.org/W2108281685","https://openalex.org/W2032527201"],"abstract_inverted_index":{"Dynamic":[0],"NeRFs":[1],"have":[2],"recently":[3],"been":[4],"used":[5],"for":[6,27,57],"3D":[7],"talking":[8,29],"portrait":[9],"synthesis,":[10],"but":[11],"challenges":[12],"remain":[13],"in":[14],"improving":[15],"efficiency":[16],"and":[17,24,72,74],"effectiveness.":[18],"We":[19,51],"introduce":[20],"R2-Talker,":[21],"an":[22],"efficient":[23],"effective":[25,58],"framework":[26],"real-time":[28],"head":[30],"synthesis.":[31],"Using":[32],"multi-resolution":[33],"hash":[34],"grids,":[35],"we":[36],"losslessly":[37],"encode":[38],"facial":[39,48],"landmarks":[40],"as":[41],"conditional":[42,59],"features,":[43],"aligning":[44],"the":[45],"structure":[46],"with":[47],"expression":[49],"movement.":[50],"also":[52],"propose":[53],"progressive":[54],"multilayer":[55],"conditioning":[56],"feature":[60],"fusion.":[61],"Compared":[62],"to":[63],"state-of-the-art":[64],"works,":[65],"our":[66],"approach":[67],"has":[68],"superior":[69],"visual":[70],"quality":[71],"accuracy,":[73],"is":[75],"computationally":[76],"efficient.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}