{"id":"https://openalex.org/W4414359947","doi":"https://doi.org/10.24963/ijcai.2025/176","title":"SyncGaussian: Stable 3D Gaussian-Based Talking Head Generation with Enhanced Lip Sync via Discriminative Speech Features","display_name":"SyncGaussian: Stable 3D Gaussian-Based Talking Head Generation with Enhanced Lip Sync via Discriminative Speech Features","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359947","doi":"https://doi.org/10.24963/ijcai.2025/176"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/176","pdf_url":"https://www.ijcai.org/proceedings/2025/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0176.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100349847","display_name":"Ke Liu","orcid":"https://orcid.org/0000-0002-3960-1124"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060342584","display_name":"Jiwei Wei","orcid":"https://orcid.org/0000-0003-3912-1742"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwei Wei","raw_affiliation_strings":["Institute of Electronic and Information Engineering of UESTC in Guangdong","University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronic and Information Engineering of UESTC in Guangdong","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114546914","display_name":"Shiyuan He","orcid":"https://orcid.org/0009-0005-6287-6969"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyuan He","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030001981","display_name":"Zeyu Ma","orcid":"https://orcid.org/0000-0002-2553-0679"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Ma","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057230698","display_name":"Chaoning Zhang","orcid":"https://orcid.org/0000-0001-6007-6099"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoning Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466084","display_name":"Ning Xie","orcid":"https://orcid.org/0000-0002-1509-464X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Xie","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Institute of Electronic and Information Engineering of UESTC in Guangdong","University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronic and Information Engineering of UESTC in Guangdong","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29162304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1576","last_page":"1584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9944999814033508,"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/T13289","display_name":"Infant Health and Development","score":0.9563000202178955,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7465999722480774},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7113000154495239},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.7095000147819519},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5483999848365784},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44780001044273376},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.44510000944137573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39649999141693115},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076000213623047},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7465999722480774},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7113000154495239},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.7095000147819519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6646999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5483999848365784},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.44510000944137573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/176","pdf_url":"https://www.ijcai.org/proceedings/2025/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/176","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/176","pdf_url":"https://www.ijcai.org/proceedings/2025/0176.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2847343476","display_name":null,"funder_award_id":"2025A1515010108","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G591136627","display_name":null,"funder_award_id":"62306067","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"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414359947.pdf","grobid_xml":"https://content.openalex.org/works/W4414359947.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"high-fidelity":[1],"talking":[2],"heads":[3],"that":[4,62,105,144],"maintain":[5],"stable":[6,64,79],"head":[7,37,65,80,86,93],"poses":[8],"and":[9,39,48,70,108,154],"achieve":[10],"robust":[11],"lip":[12,68,98,155],"sync":[13,129],"remains":[14],"a":[15,27,59,78,102,114,127],"significant":[16],"challenge.":[17],"Although":[18],"methods":[19,148],"based":[20],"on":[21],"3D":[22],"Gaussian":[23,46,81],"Splatting":[24],"(3DGS)":[25],"offer":[26],"promising":[28],"solution":[29],"via":[30],"point-based":[31],"deformation,":[32],"they":[33],"suffer":[34],"from":[35],"inconsistent":[36],"dynamics":[38],"mismatched":[40],"mouth":[41],"movements":[42],"due":[43],"to":[44,84],"unstable":[45],"initialization":[47,82],"incomplete":[49],"speech":[50,110,124,138],"features.":[51,111],"To":[52,96],"overcome":[53],"these":[54],"limitations,":[55],"we":[56,100],"introduce":[57],"SyncGaussian,":[58],"3DGS-based":[60],"framework":[61],"ensures":[63],"poses,":[66],"enhanced":[67],"sync,":[69,99,156],"realistic":[71],"appearances":[72],"with":[73,157],"real-time":[74,161],"rendering.":[75],"SyncGaussian":[76,145],"employs":[77],"strategy":[83],"mitigate":[85],"jitter":[87],"by":[88,113],"optimizing":[89],"commonly":[90],"used":[91],"rough":[92],"pose":[94],"parameters.":[95],"enhance":[97],"propose":[101],"sync-enhanced":[103],"encoder":[104,121],"leverages":[106],"audio-to-text":[107],"audio-to-visual":[109],"Guided":[112],"tailored":[115],"cosine":[116],"similarity":[117],"loss":[118],"function,":[119],"the":[120,133,158],"integrates":[122],"discriminative":[123],"features":[125],"through":[126],"multi-level":[128],"adaptation":[130],"mechanism,":[131],"enabling":[132],"learning":[134],"of":[135],"an":[136],"adaptive":[137],"feature":[139],"space.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"outperforms":[146],"state-of-the-art":[147],"in":[149],"image":[150],"quality,":[151],"dynamic":[152],"motion,":[153],"potential":[159],"for":[160],"applications.":[162]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
