{"id":"https://openalex.org/W4417100214","doi":"https://doi.org/10.1109/wacv61042.2026.00421","title":"VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework","display_name":"VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417100214","doi":"https://doi.org/10.1109/wacv61042.2026.00421"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.10269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102657624","display_name":"Donglin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421320","display_name":"Yang Li","orcid":"https://orcid.org/0000-0001-7441-7712"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongyuan Li","raw_affiliation_strings":["Image Derivative Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Image Derivative Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102282086","display_name":"Tianhang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhang Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110324800","display_name":"Junkai Huang","orcid":"https://orcid.org/0009-0004-3624-1137"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junming Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078055210","display_name":"Xiaoda Yang","orcid":"https://orcid.org/0000-0003-2282-6594"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoda Yang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100974683","display_name":"Chi Wang","orcid":"https://orcid.org/0000-0003-1686-2687"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101844050","display_name":"Weiwei Xu","orcid":"https://orcid.org/0000-0003-3756-3539"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Xu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0085298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4325","last_page":"4334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.7731000185012817,"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/T12290","display_name":"Human Motion and Animation","score":0.7731000185012817,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.05990000069141388,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.052000001072883606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7272999882698059},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7146999835968018},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6158000230789185},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.46560001373291016},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4569000005722046},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4117000102996826},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.38199999928474426},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3815000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273000121116638},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7272999882698059},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7146999835968018},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146000027656555},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5655999779701233},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.46560001373291016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3815000057220459},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3605000078678131},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.10269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10269","pdf_url":"https://arxiv.org/pdf/2510.10269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.10269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.10269","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.10269","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10269","pdf_url":"https://arxiv.org/pdf/2510.10269","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"for":[1,44],"audio-":[2],"and":[3,14,25,28,53,69,106,125,135,156,164],"pose-driven":[4],"human":[5,48],"animation":[6],"methods":[7],"often":[8],"struggle":[9],"with":[10,150],"stiff":[11],"head":[12,26,108],"movements":[13,27],"blurry":[15],"hands,":[16],"primarily":[17],"due":[18],"to":[19,65,102],"the":[20,29,67],"weak":[21],"correlation":[22],"between":[23],"audio":[24,52],"structural":[30],"complexity":[31],"of":[32,72],"hands.":[33],"To":[34],"address":[35],"these":[36],"issues,":[37],"we":[38,76,95,116],"propose":[39],"VividAnimator,":[40],"an":[41],"end-to-end":[42],"framework":[43,59],"generating":[45],"high-quality,":[46],"half-body":[47],"animations":[49],"driven":[50],"by":[51,129,160],"sparse":[54],"hand":[55,87,92,152],"pose":[56,109,127],"conditions.":[57],"Our":[58],"introduces":[60],"three":[61],"key":[62],"innovations.":[63],"First,":[64],"overcome":[66],"instability":[68],"high":[70],"cost":[71],"online":[73],"codebook":[74],"training,":[75],"pre-train":[77],"a":[78,97,118],"Hand":[79],"Clarity":[80],"Codebook":[81],"(HCC)":[82],"that":[83,123,142],"encodes":[84],"rich,":[85],"high-fidelity":[86],"texture":[88],"priors,":[89],"significantly":[90],"mitigating":[91],"degradation.":[93],"Second,":[94],"design":[96],"Dual-Stream":[98],"Audio-Aware":[99],"Module":[100],"(DSAA)":[101],"model":[103],"lip":[104],"synchronization":[105],"natural":[107,136],"dynamics":[110],"separately":[111],"while":[112],"enabling":[113],"interaction.":[114],"Third,":[115],"introduce":[117],"Pose":[119],"Calibration":[120],"Trick":[121],"(PCT)":[122],"refines":[124],"aligns":[126],"conditions":[128],"relaxing":[130],"rigid":[131],"constraints,":[132],"ensuring":[133],"smooth":[134],"gesture":[137,154],"transitions.":[138],"Extensive":[139],"experiments":[140],"demonstrate":[141],"Vivid":[143],"Animator":[144],"achieves":[145],"state-of-the-art":[146],"performance,":[147],"producing":[148],"videos":[149],"superior":[151],"detail,":[153],"realism,":[155],"identity":[157],"consistency,":[158],"validated":[159],"both":[161],"quantitative":[162],"metrics":[163],"qualitative":[165],"evaluations.":[166]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-15T00:00:00"}
