{"id":"https://openalex.org/W4400527808","doi":"https://doi.org/10.1109/fg59268.2024.10582008","title":"Giving a Hand to Diffusion Models: A Two-Stage Approach to Improving Conditional Human Image Generation","display_name":"Giving a Hand to Diffusion Models: A Two-Stage Approach to Improving Conditional Human Image Generation","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400527808","doi":"https://doi.org/10.1109/fg59268.2024.10582008"},"language":"en","primary_location":{"id":"doi:10.1109/fg59268.2024.10582008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10582008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","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/A5090329344","display_name":"Anton Pelykh","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Anton Pelykh","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055148145","display_name":"\u00d6zge Mercano\u011flu Sincan","orcid":"https://orcid.org/0000-0001-9131-0634"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ozge Mercanoglu Sincan","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044490167","display_name":"Richard Bowden","orcid":"https://orcid.org/0000-0003-3285-8020"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Bowden","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090329344"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.4352,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78035512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8773000240325928,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8773000240325928,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.8655999898910522,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8526999950408936,"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":0.6092705726623535},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6050048470497131},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5437116026878357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4576226472854614},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4576167166233063},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40917539596557617},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10366004705429077},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07534173130989075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6092705726623535},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6050048470497131},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5437116026878357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4576226472854614},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4576167166233063},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40917539596557617},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10366004705429077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07534173130989075},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/fg59268.2024.10582008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg59268.2024.10582008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"significant":[4],"progress":[5],"in":[6,14,75,94,107,145,185],"human":[7,51,222],"image":[8,52,190,223],"generation,":[9,53],"particularly":[10],"with":[11],"the":[12,29,37,55,67,72,91,95,108,113,116,120,131,135,140,154,159,170,176,195,203,206,218],"advancements":[13],"diffusion":[15,19],"models.":[16],"However,":[17],"existing":[18],"methods":[20],"encounter":[21],"challenges":[22],"when":[23],"producing":[24,119],"consistent":[25],"hand":[26,38,60,73,82,132,215],"anatomy":[27],"and":[28,62,84,89,166,189],"generated":[30,117,207],"images":[31,83],"often":[32],"lack":[33],"precise":[34],"control":[35,213],"over":[36,182,214],"pose.":[39],"To":[40],"address":[41],"this":[42],"limitation,":[43],"we":[44],"introduce":[45],"a":[46,76,146,164],"novel":[47,124],"approach":[48,199],"to":[49,79,111,129,162],"pose-conditioned":[50,221],"dividing":[54],"process":[56],"into":[57],"two":[58],"stages:":[59],"generation":[61],"subsequent":[63],"body":[64,114],"outpainting":[65],"around":[66,115],"hands.":[68],"We":[69],"propose":[70],"training":[71],"generator":[74],"multi-task":[77],"setting":[78],"produce":[80],"both":[81,143,186],"their":[85],"corresponding":[86],"segmentation":[87],"masks,":[88],"employ":[90],"trained":[92],"model":[93,103],"first":[96],"stage":[97,110,137],"of":[98,142,153,169,178,205,220],"generation.":[99,224],"An":[100],"adapted":[101],"ControlNet":[102],"is":[104,127,228],"then":[105],"used":[106],"second":[109,136],"outpaint":[112],"hands,":[118],"final":[121,171],"result.":[122],"A":[123],"blending":[125],"technique":[126],"introduced":[128],"preserve":[130],"details":[133],"during":[134],"that":[138],"combines":[139],"results":[141],"stages":[144],"coherent":[147],"way.":[148],"This":[149],"involves":[150],"sequential":[151],"expansion":[152],"outpainted":[155],"region":[156],"while":[157],"fusing":[158],"latent":[160],"representations,":[161],"ensure":[163],"seamless":[165],"cohesive":[167],"synthesis":[168],"image.":[172],"Experimental":[173],"evaluations":[174],"demonstrate":[175],"superiority":[177],"our":[179],"proposed":[180],"method":[181],"state-of-the-art":[183],"techniques,":[184],"pose":[187],"accuracy":[188],"quality,":[191],"as":[192],"validated":[193],"on":[194],"HaGRID":[196],"dataset.":[197],"Our":[198],"not":[200],"only":[201],"enhances":[202],"quality":[204],"hands":[208],"but":[209],"also":[210],"offers":[211],"improved":[212],"pose,":[216],"advancing":[217],"capabilities":[219],"The":[225],"source":[226],"code":[227],"available":[229],"here.<sup":[230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[231,233],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[232],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>https://github.com/apelykh/hand-to-diffusion":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}