{"id":"https://openalex.org/W4407128586","doi":"https://doi.org/10.1109/iccv51701.2025.01285","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","display_name":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407128586","doi":"https://doi.org/10.1109/iccv51701.2025.01285"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104265865","display_name":"Gaojie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gaojie Lin","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091605602","display_name":"Jianwen Jiang","orcid":"https://orcid.org/0009-0004-6188-6260"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianwen Jiang","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619615","display_name":"Jiaqi Yang","orcid":"https://orcid.org/0000-0002-2071-2457"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaqi Yang","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074081252","display_name":"Zerong Zheng","orcid":"https://orcid.org/0000-0003-1339-2480"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zerong Zheng","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048046659","display_name":"C. Liang","orcid":"https://orcid.org/0000-0003-3101-5021"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chao Liang","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jingtuo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jingtuo Liu","raw_affiliation_strings":["ByteDance Intelligent Creation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Intelligent Creation","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210153682"],"apc_list":null,"apc_paid":null,"fwci":0.8021,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67367612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13848","last_page":"13858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9988999962806702,"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":0.9988999962806702,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.9639999866485596,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6777785420417786},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6466114521026611},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6393431425094604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4090896248817444},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3728175759315491},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.33433663845062256},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.2868654131889343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23348253965377808},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.16320565342903137},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13891562819480896}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6777785420417786},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6466114521026611},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6393431425094604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4090896248817444},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3728175759315491},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.33433663845062256},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.2868654131889343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23348253965377808},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.16320565342903137},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13891562819480896},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.01061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01061","pdf_url":"https://arxiv.org/pdf/2502.01061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2502.01061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2502.01061","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01061","pdf_url":"https://arxiv.org/pdf/2502.01061","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310844315","https://openalex.org/W2532377291","https://openalex.org/W2000013817","https://openalex.org/W4296190881","https://openalex.org/W2366362996","https://openalex.org/W2517624617","https://openalex.org/W2378422373","https://openalex.org/W2129566390","https://openalex.org/W2360905385","https://openalex.org/W2215755978"],"abstract_inverted_index":{"End-to-end":[0],"human":[1,7,95],"animation,":[2],"such":[3],"as":[4,26],"audio-driven":[5,131],"talking":[6,112],"generation,":[8,90],"has":[9],"undergone":[10],"notable":[11],"advancements":[12],"in":[13,35,145],"the":[14,57,74,164],"recent":[15],"few":[16],"years.":[17],"However,":[18],"existing":[19,129],"methods":[20],"still":[21],"struggle":[22],"to":[23,85,128],"scale":[24],"up":[25,50],"large":[27],"general":[28],"video":[29,96],"generation":[30],"models,":[31],"limiting":[32],"their":[33],"potential":[34],"real":[36],"applications.":[37],"In":[38],"this":[39,61],"paper,":[40],"we":[41,63],"propose":[42],"OmniHuman,":[43],"a":[44],"Diffusion":[45],"Transformer-based":[46],"framework":[47],"that":[48],"scales":[49],"data":[51],"by":[52],"mixing":[53],"motion-related":[54],"conditions":[55],"into":[56],"training":[58,66],"phase.":[59],"To":[60],"end,":[62],"introduce":[64],"two":[65],"principles":[67],"for":[68],"these":[69],"mixed":[70],"conditions,":[71],"along":[72],"with":[73],"corresponding":[75],"model":[76],"architecture":[77],"and":[78,113,118,122,155],"inference":[79],"strategy.":[80],"These":[81],"designs":[82],"enable":[83],"OmniHuman":[84,100,133],"fully":[86],"leverage":[87],"data-driven":[88],"motion":[89],"ultimately":[91],"achieving":[92],"highly":[93],"realistic":[94,138],"generation.":[97],"More":[98],"importantly,":[99],"supports":[101,110,149],"various":[102],"portrait":[103],"contents":[104],"(face":[105],"close-up,":[106],"portrait,":[107],"half-body,":[108],"full-body),":[109],"both":[111],"singing,":[114],"handles":[115],"human-object":[116],"interactions":[117],"challenging":[119],"body":[120],"poses,":[121],"accommodates":[123],"different":[124],"image":[125],"styles.":[126],"Compared":[127],"end-to-end":[130],"methods,":[132],"not":[134],"only":[135],"produces":[136],"more":[137],"videos,":[139],"but":[140],"also":[141,148],"offers":[142],"greater":[143],"flexibility":[144],"inputs.":[146],"It":[147],"multiple":[150],"driving":[151,157],"modalities":[152],"(audio-driven,":[153],"video-driven":[154],"combined":[156],"signals).":[158],"Video":[159],"samples":[160],"are":[161],"provided":[162],"on":[163],"ttfamily":[165],"project":[166],"page":[167],"(https://omnihuman-lab.github.io)":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}