{"id":"https://openalex.org/W7160304198","doi":"https://doi.org/10.1109/wacv61042.2026.00372","title":"MuseDance: A Diffusion-based Music-Driven Image Animation System","display_name":"MuseDance: A Diffusion-based Music-Driven Image Animation System","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160304198","doi":"https://doi.org/10.1109/wacv61042.2026.00372"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00372","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":["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/A5009221862","display_name":"Zhikang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhikang Dong","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101711951","display_name":"Weituo Hao","orcid":"https://orcid.org/0000-0002-0031-9236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weituo Hao","raw_affiliation_strings":["Bytedance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["Bytedance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135397371","display_name":"Peng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090692960","display_name":"Pawe\u0142 Polak","orcid":"https://orcid.org/0000-0001-6645-015X"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pawel Polak","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3813","last_page":"3824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.23399999737739563,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.23399999737739563,"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/T12290","display_name":"Human Motion and Animation","score":0.1770000010728836,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.09030000120401382,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/image","display_name":"Image (mathematics)","score":0.36559998989105225},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.32589998841285706},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2937000095844269},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2890999913215637},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.2685999870300293},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.26460000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6295999884605408},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6022999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5274999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C44185422","wikidata":"https://www.wikidata.org/wiki/Q6002064","display_name":"Image-based modeling and rendering","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00372","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2149321585","https://openalex.org/W2962785568","https://openalex.org/W2963092440","https://openalex.org/W2963876278","https://openalex.org/W2964033924","https://openalex.org/W2964245526","https://openalex.org/W2984529706","https://openalex.org/W2991019415","https://openalex.org/W3035574324","https://openalex.org/W3141200356","https://openalex.org/W3175471114","https://openalex.org/W3178284600","https://openalex.org/W3196974791","https://openalex.org/W3204221554","https://openalex.org/W3206996142","https://openalex.org/W4200095354","https://openalex.org/W4231269648","https://openalex.org/W4294541506","https://openalex.org/W4312423208","https://openalex.org/W4312473638","https://openalex.org/W4312671789","https://openalex.org/W4312933868","https://openalex.org/W4372263379","https://openalex.org/W4385483513","https://openalex.org/W4385489956","https://openalex.org/W4386065807","https://openalex.org/W4386071957","https://openalex.org/W4386075767","https://openalex.org/W4390190572","https://openalex.org/W4390873054","https://openalex.org/W4390874168","https://openalex.org/W4390874580","https://openalex.org/W4393147998","https://openalex.org/W4394592978","https://openalex.org/W4395029665","https://openalex.org/W4402704510","https://openalex.org/W4402715838","https://openalex.org/W4402716510","https://openalex.org/W4402727180","https://openalex.org/W4402952275","https://openalex.org/W4404953617","https://openalex.org/W4408354016","https://openalex.org/W4409263382","https://openalex.org/W4413156551","https://openalex.org/W4415184666","https://openalex.org/W7160184662"],"related_works":[],"abstract_inverted_index":{"Image":[0],"animation":[1,35],"is":[2,175],"a":[3,11,61,126,160],"rapidly":[4],"developing":[5],"area":[6],"in":[7,121],"multimodal":[8,128],"research,":[9],"with":[10,80,137],"focus":[12],"on":[13],"generating":[14],"videos":[15,67],"from":[16],"reference":[17,49],"images.":[18],"While":[19],"much":[20],"of":[21,85,109,131,166,172],"the":[22,81,86,93,107,138,164],"work":[23,174],"has":[24],"emphasized":[25],"generic":[26],"video":[27,110],"generation":[28,111],"guided":[29],"by":[30],"text,":[31],"music-driven":[32,167],"dance":[33,133],"image":[34,168],"remains":[36],"underexplored.":[37],"In":[38],"this":[39,122,173],"paper,":[40],"we":[41,124],"introduce":[42],"MuseDance,":[43],"an":[44],"end-to-end":[45],"model":[46],"that":[47,68],"animates":[48],"images":[50],"using":[51],"both":[52],"music":[53,59,141],"and":[54,83,115,142,156],"text":[55,143],"inputs.":[56],"By":[57],"integrating":[58],"as":[60,100],"conditioning":[62],"modality,":[63],"MuseDance":[64,91],"generates":[65],"personalized":[66],"not":[69],"only":[70],"adhere":[71],"to":[72,150],"textual":[73],"descriptions":[74],"but":[75],"also":[76],"synchronize":[77],"character":[78],"movements":[79],"rhythm":[82],"dynamics":[84],"music.":[87],"Unlike":[88],"existing":[89],"methods,":[90],"eliminates":[92],"need":[94],"for":[95,163],"explicit":[96],"motion":[97],"guidance,":[98],"such":[99],"pose":[101],"sequences":[102],"or":[103],"depth":[104],"maps,":[105],"reducing":[106],"complexity":[108],"while":[112],"enhancing":[113],"accessibility":[114],"flexibility.":[116],"To":[117],"support":[118],"further":[119],"research":[120],"field,":[123],"present":[125],"new":[127,161],"dataset":[129,171],"comprising":[130],"3,122":[132],"videos,":[134],"each":[135],"paired":[136],"corresponding":[139],"background":[140],"descriptions.":[144],"Our":[145],"approach":[146],"leverages":[147],"diffusion-based":[148],"methods":[149],"achieve":[151],"robust":[152],"generalization,":[153],"precise":[154],"control,":[155],"temporal":[157],"consistency,":[158],"setting":[159],"benchmark":[162],"task":[165],"animation.":[169],"The":[170],"available":[176],"at":[177],"https://github.com/Dongzhikang/musedance.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}
