{"id":"https://openalex.org/W7146996990","doi":"https://doi.org/10.1109/cnml68938.2026.11453127","title":"Region-Aware Deformable Gaussian Splatting for Audio-Driven Talking Head Synthesis","display_name":"Region-Aware Deformable Gaussian Splatting for Audio-Driven Talking Head Synthesis","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7146996990","doi":"https://doi.org/10.1109/cnml68938.2026.11453127"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11453127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-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/A5100773692","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-0657-1600"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuli Tian","raw_affiliation_strings":["University of Science and Technology of China,School of Cybersecurity,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cybersecurity,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132609647","display_name":"Yong Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liao","raw_affiliation_strings":["University of Science and Technology of China,School of Cybersecurity,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Cybersecurity,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100773692"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89847736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8881000280380249,"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":0.8881000280380249,"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":0.07980000227689743,"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":0.0038999998942017555,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5482000112533569},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.36910000443458557},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.34360000491142273},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.3400000035762787},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6848000288009644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.684499979019165},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C3018868555","wikidata":"https://www.wikidata.org/wiki/Q2918907","display_name":"Single camera","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11453127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11453127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2107037917","https://openalex.org/W2738406145","https://openalex.org/W2914217321","https://openalex.org/W3006295631","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3211147706","https://openalex.org/W4385318467","https://openalex.org/W4386066256","https://openalex.org/W4390872116","https://openalex.org/W4395065528","https://openalex.org/W4402726971","https://openalex.org/W4403998628","https://openalex.org/W4415280018","https://openalex.org/W4415795645"],"related_works":[],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,50],"head":[2,51,55],"synthesis":[3],"is":[4,84,101],"a":[5,31,44,60,69,74],"fundamental":[6],"component":[7],"in":[8,121],"immersive":[9],"media":[10],"systems":[11],"and":[12,26,36,59,73,106,126],"digital":[13],"human":[14],"animation.":[15],"Recently,":[16],"3D":[17,28,45],"Gaussian":[18,71],"Splatting":[19],"has":[20],"been":[21],"explored":[22],"as":[23],"an":[24,97],"explicit":[25],"efficient":[27],"representation,":[29],"providing":[30],"new":[32],"solution":[33],"for":[34,48],"high-quality":[35],"real-time":[37],"rendering.":[38],"In":[39,95],"this":[40],"work,":[41],"we":[42],"present":[43],"Gaussian-based":[46],"framework":[47],"audio-driven":[49],"generation.":[52],"A":[53],"stable":[54],"pose":[56],"estimation":[57],"strategy":[58],"structured":[61],"facial":[62,93],"geometric":[63],"prior":[64],"are":[65],"introduced":[66],"to":[67,86,103],"initialize":[68],"canonical":[70],"field,":[72],"region-decoupled":[75],"deformation":[76],"prediction":[77],"module":[78,100],"together":[79],"with":[80],"region-aware":[81],"audio":[82],"modulation":[83],"designed":[85],"model":[87],"the":[88,115],"dynamic":[89],"characteristics":[90],"of":[91],"different":[92],"regions.":[94,110],"addition,":[96],"adaptive":[98],"fusion":[99],"proposed":[102,116],"achieve":[104],"smooth":[105],"natural":[107],"transitions":[108],"between":[109],"Experimental":[111],"evaluations":[112],"show":[113],"that":[114],"approach":[117],"delivers":[118],"strong":[119],"performance":[120],"reconstruction":[122],"quality,":[123],"lip":[124],"synchronization,":[125],"rendering":[127],"efficiency.":[128]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}