{"id":"https://openalex.org/W7167260189","doi":"https://doi.org/10.1145/3811361","title":"HumanFlow: Controllable Human Image Generation via Flow Matching","display_name":"HumanFlow: Controllable Human Image Generation via Flow Matching","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W7167260189","doi":"https://doi.org/10.1145/3811361"},"language":"en","primary_location":{"id":"doi:10.1145/3811361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811361","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3811361","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112946580","display_name":"Wenzhuo Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhuo Fan","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, HuBei, China"],"raw_orcid":"https://orcid.org/0009-0005-1258-5442","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210111616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054511641","display_name":"Hongsheng Zheng","orcid":"https://orcid.org/0000-0003-1274-3373"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsheng Zheng","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, HuBei, China"],"raw_orcid":"https://orcid.org/0000-0003-1274-3373","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210111616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079932295","display_name":"Jianchi Sun","orcid":"https://orcid.org/0000-0003-2256-6294"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchi Sun","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, HuBei, China"],"raw_orcid":"https://orcid.org/0000-0003-2256-6294","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210111616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110933388","display_name":"Fei Fang","orcid":"https://orcid.org/0009-0005-7920-4843"},"institutions":[{"id":"https://openalex.org/I4210119942","display_name":"Wuhan Textile University","ror":"https://ror.org/02jgsf398","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210119942"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Wuhan Textile University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0005-7920-4843","affiliations":[{"raw_affiliation_string":"Wuhan Textile University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210119942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007786","display_name":"Hong Ding","orcid":"https://orcid.org/0000-0001-9946-2448"},"institutions":[{"id":"https://openalex.org/I163732180","display_name":"Guangxi University of Finance and Economics","ror":"https://ror.org/02ayg6516","country_code":"CN","type":"education","lineage":["https://openalex.org/I163732180"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Ding","raw_affiliation_strings":["Guangxi University of Finance and Economic, Nanning, GuangXi, China"],"raw_orcid":"https://orcid.org/0000-0001-9946-2448","affiliations":[{"raw_affiliation_string":"Guangxi University of Finance and Economic, Nanning, GuangXi, China","institution_ids":["https://openalex.org/I163732180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768160","display_name":"Chunxia Xiao","orcid":"https://orcid.org/0000-0002-4526-6297"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxia Xiao","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, HuBei, China"],"raw_orcid":"https://orcid.org/0000-0002-4526-6297","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, HuBei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210111616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.89033867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"4","first_page":"1","last_page":"17"},"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":0.8496999740600586,"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":0.8496999740600586,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05939999967813492,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/encoder","display_name":"Encoder","score":0.6065999865531921},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5238999724388123},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.510200023651123},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4715000092983246},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.40939998626708984},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700000166893005},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.510200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49559998512268066},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C189216461","wikidata":"https://www.wikidata.org/wiki/Q2443456","display_name":"Topology optimization","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3811361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811361","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3811361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811361","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6598994868","display_name":null,"funder_award_id":"62372336","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2302255633","https://openalex.org/W4311805945","https://openalex.org/W4312782988","https://openalex.org/W4312933868","https://openalex.org/W4385271134","https://openalex.org/W4386057725","https://openalex.org/W4386072096","https://openalex.org/W4390871780","https://openalex.org/W4390873054","https://openalex.org/W4393148714","https://openalex.org/W4393149063","https://openalex.org/W4400582405","https://openalex.org/W4402715797","https://openalex.org/W4402753746","https://openalex.org/W4402753991","https://openalex.org/W4402754267","https://openalex.org/W4403021798","https://openalex.org/W4409348103","https://openalex.org/W4409366120","https://openalex.org/W4409366296","https://openalex.org/W4409367237","https://openalex.org/W4409369458","https://openalex.org/W4412588068","https://openalex.org/W4413145448","https://openalex.org/W4413146187","https://openalex.org/W4413146481","https://openalex.org/W4413147741","https://openalex.org/W4413156548","https://openalex.org/W4415795232","https://openalex.org/W4416016078","https://openalex.org/W4417124887","https://openalex.org/W4417125861","https://openalex.org/W7137860570","https://openalex.org/W7160094899","https://openalex.org/W7160149704","https://openalex.org/W7160184945","https://openalex.org/W7160185424"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"HumanFlow,":[2],"a":[3,29,50,70,86,101,140,165],"unified":[4,71,87],"flow-matching-based":[5,208],"framework":[6,73],"that":[7,90,196],"enables":[8],"high-fidelity":[9],"and":[10,77,152,159,181,188,207],"controllable":[11,24],"full-body":[12,174],"human":[13,25,46,118,137,167,175],"image":[14,26,47,96,168],"generation":[15,27,48,56],"under":[16],"diverse":[17,83],"human-centric":[18,41,61,183],"control":[19,42,62,72,103,116,184],"conditions.":[20,43,185],"Despite":[21],"recent":[22],"progress,":[23],"poses":[28],"fundamental":[30],"challenge":[31],"in":[32],"balancing":[33],"high":[34,212],"visual":[35,213],"fidelity":[36],"with":[37,54,74,94,107,177],"strict":[38],"adherence":[39],"to":[40,139],"HumanFlow":[44,197],"formulates":[45],"as":[49],"conditional":[51,131],"flow-matching":[52],"process":[53],"deterministic":[55],"dynamics.":[57],"To":[58,112,155],"incorporate":[59],"such":[60],"conditions":[63,84],"into":[64,85],"the":[65,95,108,123,192,204],"pretrained":[66],"model,":[67],"we":[68,120,162],"introduce":[69],"Control":[75,80],"Encoder":[76,81],"Token-ControlNet.":[78],"A":[79],"maps":[82],"latent":[88,97],"representation":[89],"is":[91,100],"spatially":[92],"aligned":[93,106,178],"space.":[98],"Token-ControlNet":[99],"lightweight":[102],"network":[104],"architecturally":[105],"FLUX":[109],"double-stream":[110],"design.":[111],"address":[113],"accurate":[114],"structural":[115,201],"over":[117,171],"bodies,":[119],"further":[121],"propose":[122],"Human":[124],"Topology":[125],"Consistency":[126],"Loss":[127],"(HTCL).":[128],"HTCL":[129],"regularizes":[130],"flow":[132],"matching":[133],"by":[134,148],"constraining":[135],"generated":[136],"configurations":[138],"union":[141],"of":[142],"statistically":[143],"grounded":[144],"topology":[145],"manifolds":[146],"defined":[147],"normalized":[149],"bone":[150],"ratios":[151],"joint":[153],"angles.":[154],"support":[156],"large-scale":[157],"training":[158],"systematic":[160],"evaluation,":[161],"construct":[163],"MiCoGen,":[164],"multi-condition":[166],"dataset":[169,194],"comprising":[170],"one":[172],"million":[173],"images":[176],"text":[179],"descriptions":[180],"rich":[182],"Extensive":[186],"quantitative":[187],"qualitative":[189],"evaluations":[190],"on":[191],"MiCoGen":[193],"show":[195],"consistently":[198],"achieves":[199],"improved":[200],"consistency":[202],"than":[203],"existing":[205],"diffusion-based":[206],"methods,":[209],"while":[210],"maintaining":[211],"fidelity.":[214]},"counts_by_year":[],"updated_date":"2026-07-04T06:14:54.683239","created_date":"2026-07-04T00:00:00"}