{"id":"https://openalex.org/W4413147584","doi":"https://doi.org/10.1109/cvpr52734.2025.01482","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","display_name":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147584","doi":"https://doi.org/10.1109/cvpr52734.2025.01482"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5086870826","display_name":"Enric Corona","orcid":"https://orcid.org/0000-0002-4835-1868"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Enric Corona","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038554615","display_name":"Andrei Zanfir","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Andrei Zanfir","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014477991","display_name":"Eduard Gabriel B\u0103z\u0103van","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Eduard Gabriel Bazavan","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048259380","display_name":"Nikos Kolotouros","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Nikos Kolotouros","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072771954","display_name":"Thiemo Alldieck","orcid":"https://orcid.org/0000-0002-9107-4173"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Thiemo Alldieck","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007658897","display_name":"Cristian Sminchisescu","orcid":"https://orcid.org/0000-0001-5256-886X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Cristian Sminchisescu","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":37.2616,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9985794,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"15896","last_page":"15908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9860000014305115,"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":0.9860000014305115,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9700000286102295,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9337000250816345,"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/avatar","display_name":"Avatar","score":0.846877932548523},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7597191333770752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7014868259429932},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5460562109947205},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4225867986679077},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42244040966033936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2500578761100769},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0473533570766449}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.846877932548523},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7597191333770752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7014868259429932},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5460562109947205},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4225867986679077},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42244040966033936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2500578761100769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0473533570766449},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W3196465490","https://openalex.org/W2035104213","https://openalex.org/W2240967841","https://openalex.org/W2791686160","https://openalex.org/W1513257435","https://openalex.org/W2289840258","https://openalex.org/W2503352526","https://openalex.org/W2548809491","https://openalex.org/W2968405290","https://openalex.org/W2960696728"],"abstract_inverted_index":{"We":[0,135,194],"propose":[1],"VLOGGER,":[2],"a":[3,11,16,33,40,114,139,218],"method":[4,29,85],"for":[5,90],"audio-driven":[6],"human":[7,75],"video":[8,61,230],"generation":[9,57],"from":[10],"single":[12],"input":[13],"image":[14,104,182],"of":[15,23,31,58,62,74,117,152,198,214],"person,":[17,92],"which":[18],"builds":[19],"on":[20,96],"the":[21,56,102,107,110,196,212],"success":[22],"recent":[24],"generative":[25],"diffusion":[26,36],"models.":[27],"Our":[28],"consists":[30],"1)":[32],"stochastic":[34],"human-to-3d-motion":[35],"model,":[37],"and":[38,51,77,99,112,141,147,160,167,186,211,220,232],"2)":[39],"novel":[41],"diffusion-based":[42],"architecture":[43],"that":[44,126,207],"augments":[45],"text-to-image":[46],"models":[47],"with":[48,144,161,200],"both":[49],"spatial":[50],"temporal":[52,187],"controls.":[53],"This":[54],"supports":[55],"high":[59],"quality":[60],"variable":[63],"length,":[64],"easily":[65],"controllable":[66],"through":[67],"text":[68],"or":[69,109,122],"speech":[70],"via":[71],"high-level":[72],"representations":[73],"faces":[76],"bodies.":[78],"In":[79],"contrast":[80],"to":[81,129,202],"previous":[82,156],"work,":[83],"our":[84,169,208],"does":[86,93],"not":[87,94],"require":[88],"training":[89,217],"each":[91],"rely":[95],"face":[97,108],"detection":[98],"cropping,":[100],"generates":[101],"complete":[103],"(not":[105],"just":[106],"lips),":[111],"considers":[113],"broad":[115],"spectrum":[116],"scenarios":[118],"(e.g.":[119],"visible":[120],"torso":[121],"diverse":[123,142],"subject":[124],"identities)":[125,159],"are":[127],"critical":[128],"correctly":[130],"synthesize":[131],"humans":[132],"who":[133],"communicate.":[134],"also":[136,190],"curate":[137],"MENTOR,":[138],"new":[140],"dataset":[143],"3d":[145],"pose":[146],"expression":[148],"annotations,":[149],"one":[150],"order":[151],"magnitude":[153],"larger":[154],"than":[155],"ones":[157],"(800,000":[158],"dynamic":[162],"gestures,":[163],"where":[164],"we":[165,226],"train":[166],"ablate":[168],"main":[170],"technical":[171],"contributions.":[172],"VLOGGER":[173,199],"outperforms":[174],"state-of-the-art":[175],"methods":[176],"in":[177,229],"three":[178],"public":[179],"benchmarks,":[180],"considering":[181],"quality,":[183],"identity":[184],"preservation":[185],"consistency":[188],"while":[189],"generating":[191],"upperbody":[192],"gestures.":[193],"analyze":[195],"performance":[197],"respect":[201],"multiple":[203],"diversity":[204],"metrics,":[205],"showing":[206],"architectural":[209],"choices":[210],"use":[213],"MENTOR":[215],"benefit":[216],"fair":[219],"unbiased":[221],"model":[222],"at":[223],"scale.":[224],"Finally":[225],"show":[227],"applications":[228],"editing":[231],"personalization.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}