{"id":"https://openalex.org/W7140106201","doi":"https://doi.org/10.48550/arxiv.2603.20012","title":"Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features","display_name":"Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140106201","doi":"https://doi.org/10.48550/arxiv.2603.20012"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.20012","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.20012","pdf_url":"https://arxiv.org/pdf/2603.20012","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.20012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130411419","display_name":"Zheng Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gao, Zheng","raw_affiliation_strings":["Queen Mary University of London ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London ,","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073252742","display_name":"Debin Meng","orcid":"https://orcid.org/0009-0002-0430-0660","observed_orcids":["https://orcid.org/0009-0002-0430-0660"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Debin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126678771","display_name":"Yunqi Miao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao, Yunqi","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128023421","display_name":"Zhensong Zhang","orcid":"https://orcid.org/0009-0001-7911-7564","observed_orcids":["https://orcid.org/0009-0001-7911-7564"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhensong","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130328245","display_name":"Songcen Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Songcen","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031205865","display_name":"Ioannis Patras","orcid":"https://orcid.org/0000-0003-3913-4738","observed_orcids":["https://orcid.org/0000-0003-3913-4738"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patras, Ioannis","raw_affiliation_strings":["Queen Mary University of London ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London ,","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046874089","display_name":"Jifei Song","orcid":"https://orcid.org/0000-0002-3381-6685","observed_orcids":["https://orcid.org/0000-0002-3381-6685"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song, Jifei","raw_affiliation_strings":["Huawei London Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei London Research Center","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":1.0,"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":1.0,"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":0.0,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0,"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/makeup-transfer","display_name":"makeup transfer","score":0.9890000224113464},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8539999723434448},{"id":"https://openalex.org/keywords/clip-fine-tuning","display_name":"CLIP fine-tuning","score":0.9340000152587891},{"id":"https://openalex.org/keywords/image-text-contrastive-learning","display_name":"image-text contrastive learning","score":0.8640000224113464},{"id":"https://openalex.org/keywords/controlnet","display_name":"ControlNet","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675599992275238},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6128000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.602400004863739},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38850000500679016},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.26190000772476196}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.20012","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.20012","pdf_url":"https://arxiv.org/pdf/2603.20012","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.20012","doi":"https://doi.org/10.48550/arxiv.2603.20012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20012","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:2603.20012","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.20012","pdf_url":"https://arxiv.org/pdf/2603.20012","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140106201.pdf","grobid_xml":"https://content.openalex.org/works/W7140106201.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127541424","https://openalex.org/W7170243878","https://openalex.org/W4412588161","https://openalex.org/W7142195950","https://openalex.org/W4392926855","https://openalex.org/W7165395327","https://openalex.org/W6966958218","https://openalex.org/W4415798526","https://openalex.org/W4402982660","https://openalex.org/W4410065003"],"abstract_inverted_index":{"Current":[0],"diffusion-based":[1],"makeup":[2,8,22,48,52,69,75,88,108,116,119,131,149,163,168,191,201,211,218,221,264],"transfer":[3,265],"methods":[4],"commonly":[5],"use":[6,143,180,205,239],"the":[7,21,28,51,60,72,83,144,172,196,210,256],"information":[9],"encoded":[10],"by":[11],"off-the-shelf":[12,126],"foundation":[13,39],"models":[14,40],"(e.g.,":[15],"CLIP)":[16],"as":[17,64],"condition":[18],"to":[19,46,59,146,182,184,195,208,214,230,243],"preserve":[20],"style":[23,132],"of":[24,54,187,192,258],"reference":[25,55,193],"image":[26,56,138,169,189,194,246],"in":[27,93,175],"generation.":[29],"Although":[30],"effective,":[31],"these":[32],"works":[33,124],"mainly":[34],"have":[35],"two":[36,105],"limitations:":[37],"(1)":[38,107],"pre-trained":[41],"for":[42,67,86,200,220,235],"generic":[43],"tasks":[44],"struggle":[45],"capture":[47],"styles;":[49],"(2)":[50,111],"features":[53,76,101,219],"are":[57],"injected":[58],"diffusion":[61,197],"denoising":[62,198],"model":[63,199],"a":[65,148,240],"whole":[66],"global":[68],"transfer,":[70],"overlooking":[71],"facial":[73,114,161,216],"region-aware":[74,115,162,217],"(i.e.,":[77],"eyes,":[78],"mouth,":[79],"etc)":[80],"and":[81,113,136,141,154,160,178,190,247,262],"limiting":[82],"regional":[84,232,260],"controllability":[85,261],"region-specific":[87],"transfer.":[89,202],"To":[90],"address":[91],"these,":[92],"this":[94],"work,":[95],"we":[96,128,165,204,238],"propose":[97],"Facial":[98],"Region-Aware":[99],"Makeup":[100],"(FRAM),":[102],"which":[103,223],"has":[104],"stages:":[106],"CLIP":[109,120,150,212],"fine-tuning;":[110],"identity":[112,159,186,236],"injection.":[117],"For":[118,158],"fine-tuning,":[121],"unlike":[122],"prior":[123],"using":[125,134],"CLIP,":[127],"synthesize":[129],"annotated":[130],"data":[133,145],"GPT-o3":[135],"text-driven":[137],"editing":[139],"model,":[140],"then":[142,179],"train":[147],"encoder":[151,213],"through":[152],"self-supervised":[153],"image-text":[155],"contrastive":[156],"learning.":[157],"injection,":[164,222,237],"construct":[166],"before-and-after":[167],"pairs":[170],"from":[171],"edited":[173],"images":[174],"stage":[176],"1":[177],"them":[181],"learn":[183],"inject":[185],"source":[188,245],"Specifically,":[203],"learnable":[206],"tokens":[207],"query":[209],"extract":[215],"is":[224,268],"learned":[225],"via":[226],"an":[227],"attention":[228],"loss":[229],"enable":[231],"control.":[233],"As":[234],"ControlNet":[241],"Union":[242],"encode":[244],"its":[248],"3D":[249],"mesh":[250],"simultaneously.":[251],"The":[252],"experimental":[253],"results":[254],"verify":[255],"superiority":[257],"our":[259,263],"performance.":[266],"Code":[267],"available":[269],"at":[270],"https://github.com/zaczgao/Facial_Region-Aware_Makeup.":[271]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}