{"id":"https://openalex.org/W4413144792","doi":"https://doi.org/10.1109/cvpr52734.2025.01156","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","display_name":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144792","doi":"https://doi.org/10.1109/cvpr52734.2025.01156"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01156","doi":"https://doi.org/10.1109/cvpr52734.2025.01156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01156","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.24026","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042353520","display_name":"Bo-Yuan Wang","orcid":"https://orcid.org/0000-0003-3135-0655","observed_orcids":["https://orcid.org/0000-0003-3135-0655","https://orcid.org/0009-0002-2252-1969","https://orcid.org/0000-0002-4937-6119"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyuan Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333212","display_name":"Xiaofeng Wang","orcid":"https://orcid.org/0000-0001-6488-4034","observed_orcids":["https://orcid.org/0000-0001-6488-4034"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112069316","display_name":"Chaojun Ni","orcid":"https://orcid.org/0009-0008-7092-8310","observed_orcids":["https://orcid.org/0009-0008-7092-8310"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaojun Ni","raw_affiliation_strings":["GigaAI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GigaAI,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guosheng Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guosheng Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106457631","display_name":"Z. Q. Yang","orcid":"https://orcid.org/0000-0002-7047-2981","observed_orcids":["https://orcid.org/0000-0002-7047-2981"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiqin Yang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705530","display_name":"Zheng Dong Zhu","orcid":"https://orcid.org/0000-0002-4435-1692","observed_orcids":["https://orcid.org/0000-0002-4435-1692"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Zhu","raw_affiliation_strings":["GigaAI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GigaAI,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101567314","display_name":"Muyang Zhang","orcid":"https://orcid.org/0009-0000-1099-5804","observed_orcids":["https://orcid.org/0009-0000-1099-5804"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muyang Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129957710","display_name":"Yukun Zhou","orcid":"https://orcid.org/0000-0001-5876-620X","observed_orcids":["https://orcid.org/0000-0001-5876-620X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Zhou","raw_affiliation_strings":["GigaAI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GigaAI,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021848354","display_name":"Xinze Chen","orcid":"https://orcid.org/0009-0005-4470-7838","observed_orcids":["https://orcid.org/0009-0005-4470-7838"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinze Chen","raw_affiliation_strings":["GigaAI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GigaAI,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051049837","display_name":"Guan Huang","orcid":"https://orcid.org/0000-0002-9421-7344","observed_orcids":["https://orcid.org/0000-0002-9421-7344"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan Huang","raw_affiliation_strings":["GigaAI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GigaAI,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450896","display_name":"Lihong Liu","orcid":"https://orcid.org/0000-0002-9956-2665","observed_orcids":["https://orcid.org/0000-0002-9956-2665"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihong Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026151620","display_name":"Xingang Wang","orcid":"https://orcid.org/0000-0002-6851-0109","observed_orcids":["https://orcid.org/0000-0002-6851-0109","https://orcid.org/0000-0002-1744-8712","https://orcid.org/0000-0002-9480-8603"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingang Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7786,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.94185637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12391","last_page":"12401"},"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":0.9413999915122986,"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":0.9413999915122986,"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":0.04650000110268593,"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":0.008999999612569809,"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/text-to-video-generation","display_name":"text-to-video generation","score":0.5210000276565552},{"id":"https://openalex.org/keywords/controllable-video-generation","display_name":"controllable video generation","score":0.8299999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728878021240234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5794317722320557},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5475873947143555},{"id":"https://openalex.org/C2986578859","wikidata":"https://www.wikidata.org/wiki/Q657632","display_name":"Human motion","level":3,"score":0.4899117350578308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48642778396606445},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.47943633794784546},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.19543763995170593}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01156","doi":"https://doi.org/10.1109/cvpr52734.2025.01156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01156","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2503.24026","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24026","pdf_url":"https://arxiv.org/pdf/2503.24026","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,"listed_in":[],"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.2503.24026","doi":"https://doi.org/10.48550/arxiv.2503.24026","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.24026","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.24026","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24026","pdf_url":"https://arxiv.org/pdf/2503.24026","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4413156376","https://openalex.org/W4390872414","https://openalex.org/W7140000225","https://openalex.org/W4413156214","https://openalex.org/W4391305822","https://openalex.org/W4416373179","https://openalex.org/W4414975318","https://openalex.org/W7134835602","https://openalex.org/W4416167255","https://openalex.org/W7118864598"],"abstract_inverted_index":{"Human-motion":[0],"video":[1,27,55],"generation":[2,28,56],"has":[3],"been":[4],"a":[5,52,105,115],"challenging":[6],"task,":[7],"primarily":[8],"due":[9],"to":[10,24,71,96,114],"the":[11,79,88,141,156],"difficulty":[12],"inherent":[13],"in":[14,118,126],"learning":[15],"human":[16,54],"body":[17],"movements.":[18],"While":[19],"some":[20],"approaches":[21],"have":[22],"attempted":[23],"drive":[25],"human-centric":[26],"explicitly":[29],"through":[30],"pose":[31,84,179],"control,":[32],"these":[33,69],"methods":[34],"typically":[35],"rely":[36],"on":[37,87],"poses":[38,62,70,100,157],"derived":[39],"from":[40,63,101],"existing":[41],"videos,":[42],"thereby":[43,138],"lacking":[44],"flexibility.":[45],"To":[46],"address":[47],"this,":[48],"we":[49,76,90],"propose":[50,77],"HumanDreamer,":[51],"decoupled":[53],"framework":[57],"that":[58,155],"first":[59],"generates":[60],"diverse":[61,164],"text":[64,102],"prompts":[65],"and":[66,131,136,145,165,182],"then":[67],"leverages":[68],"generate":[72,97],"human-motion":[73,83,99,167],"videos.":[74,168],"Specifically,":[75],"MotionVid,":[78],"largest":[80],"dataset":[81],"for":[82,128],"generation.":[85],"Based":[86],"dataset,":[89],"present":[91],"MotionDiT,":[92],"which":[93,111],"is":[94,109],"trained":[95],"structured":[98],"prompts.":[103],"Besides,":[104],"novel":[106],"LAMA":[107],"loss":[108],"introduced,":[110],"together":[112],"contribute":[113],"significant":[116],"improvement":[117],"FID":[119,146],"by":[120,133,159],"62.4%,":[121],"along":[122],"with":[123],"respective":[124],"enhancements":[125],"R-precision":[127],"top1,":[129],"top2,":[130],"top3":[132],"41.8%,":[134],"26.3%,":[135],"18.3%,":[137],"advancing":[139],"both":[140],"Text-to-Pose":[142],"control":[143],"accuracy":[144],"metrics.":[147],"Our":[148],"experiments":[149],"across":[150],"various":[151],"Pose-to-Video":[152],"baselines":[153],"demonstrate":[154],"generated":[158],"our":[160,170],"method":[161],"can":[162,172],"produce":[163],"high-quality":[166],"Furthermore,":[169],"model":[171],"facilitate":[173],"other":[174],"downstream":[175],"tasks,":[176],"such":[177],"as":[178],"sequence":[180],"prediction":[181],"2D-3D":[183],"motion":[184],"lifting.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}