{"id":"https://openalex.org/W4413146187","doi":"https://doi.org/10.1109/cvpr52734.2025.00238","title":"Learning Flow Fields in Attention for Controllable Person Image Generation","display_name":"Learning Flow Fields in Attention for Controllable Person Image Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146187","doi":"https://doi.org/10.1109/cvpr52734.2025.00238"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00238","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":"article","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/A5102944236","display_name":"Zijian Zhou","orcid":"https://orcid.org/0000-0003-3315-3962"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zijian Zhou","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044687301","display_name":"Shikun Liu","orcid":"https://orcid.org/0000-0001-5942-0841"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shikun Liu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611806","display_name":"Xiao Han","orcid":"https://orcid.org/0009-0001-5725-5720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Han","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101438229","display_name":"Haozhe Liu","orcid":"https://orcid.org/0000-0003-1191-3529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhe Liu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033394573","display_name":"Kam Woh Ng","orcid":"https://orcid.org/0000-0002-9309-563X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kam Woh Ng","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102862589","display_name":"Tian Xie","orcid":"https://orcid.org/0000-0003-0204-1124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Xie","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622051","display_name":"Yuren Cong","orcid":"https://orcid.org/0000-0001-7505-8563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuren Cong","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455146","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-8486-6631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062927440","display_name":"Mengmeng Xu","orcid":"https://orcid.org/0000-0001-6379-7940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengmeng Xu","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805096","display_name":"Juan-Manuel P\u00e9rez-R\u00faa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan-Manuel P\u00e9rez-R\u00faa","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018367360","display_name":"Aditya Patel","orcid":"https://orcid.org/0000-0002-1972-547X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Patel","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014436524","display_name":"Tao Xiang","orcid":"https://orcid.org/0000-0002-2530-1059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xiang","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675323","display_name":"Miaojing Shi","orcid":"https://orcid.org/0000-0002-4933-0073"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaojing Shi","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035606153","display_name":"Sen He","orcid":"https://orcid.org/0000-0002-5204-8976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen He","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5102944236"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3383,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92870915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2491","last_page":"2501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.98580002784729,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.98580002784729,"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/T11448","display_name":"Face recognition and analysis","score":0.9311000108718872,"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/computer-science","display_name":"Computer science","score":0.6263244152069092},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5125824809074402},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4331919252872467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42596757411956787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157432019710541},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13265731930732727},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.10479825735092163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6263244152069092},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5125824809074402},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4331919252872467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42596757411956787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157432019710541},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13265731930732727},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.10479825735092163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00238","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"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/8cafac1f-dab1-4961-aff9-dda4e8f5cec7","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/8cafac1f-dab1-4961-aff9-dda4e8f5cec7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhou, Z, Liu, S, Han, X, Liu, H, Ng, K W, Xie, T, Cong, Y, Li, H, Xu, M, P\u00e9rez-R\u00faa, J-M, Patel, A, Xiang, T, Shi, M & He, S 2025, 'Learning Flow Fields in Attention for Controllable Person Image Generation', IEEE Computer Society Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR52734.2025.00238","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Controllable":[0],"person":[1,8],"image":[2,9,38,125],"generation":[3],"aims":[4],"to":[5,44,47,72,74,139],"generate":[6],"a":[7,90,100],"conditioned":[10],"on":[11,93],"reference":[12,32,52,77],"images,":[13],"allowing":[14],"precise":[15],"control":[16],"over":[17],"the":[18,31,51,69,75,80,96,141],"person\u2019s":[19],"appearance":[20,114],"or":[21],"pose.":[22],"However,":[23],"prior":[24],"methods":[25],"often":[26],"distort":[27],"fine-grained":[28,119],"details":[29],"from":[30],"image,":[33],"despite":[34],"achieving":[35],"high":[36,124],"overall":[37],"quality.":[39,126],"We":[40],"attribute":[41],"these":[42],"distortions":[43],"inadequate":[45],"attention":[46,64,81,97],"corresponding":[48],"regions":[49],"in":[50,63,79,112],"image.":[53],"To":[54],"address":[55],"this,":[56],"we":[57,128],"thereby":[58],"propose":[59],"learning":[60],"flow":[61],"fields":[62],"(Leffa),":[65],"which":[66],"explicitly":[67],"guides":[68],"target":[70],"query":[71],"attend":[73],"correct":[76],"key":[78],"layer":[82],"during":[83],"training.":[84],"Specifically,":[85],"it":[86],"is":[87,133],"realized":[88],"via":[89],"regularization":[91],"loss":[92,132],"top":[94],"of":[95,143],"map":[98],"within":[99],"diffusionbased":[101],"baseline.":[102],"Our":[103],"extensive":[104],"experiments":[105],"show":[106,129],"that":[107,130],"Leffa":[108],"achieves":[109],"state-of-the-art":[110],"performance":[111,142],"controlling":[113],"and":[115,135],"pose,":[116],"significantly":[117],"reducing":[118],"detail":[120],"distortion":[121],"while":[122],"maintaining":[123],"Additionally,":[127],"our":[131],"model-agnostic":[134],"can":[136],"be":[137],"used":[138],"improve":[140],"other":[144],"diffusion":[145],"models.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}