{"id":"https://openalex.org/W7140274347","doi":"https://doi.org/10.1145/3803012","title":"One-shot Face Sketch Synthesis in-the-Wild via Generative Diffusion Prior and Instruction Tuning","display_name":"One-shot Face Sketch Synthesis in-the-Wild via Generative Diffusion Prior and Instruction Tuning","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140274347","doi":"https://doi.org/10.1145/3803012"},"language":"en","primary_location":{"id":"doi:10.1145/3803012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3803012","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5100593697","display_name":"Han Wu","orcid":"https://orcid.org/0009-0005-8371-9997"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Wu","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-8371-9997","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyao Li","orcid":"https://orcid.org/0009-0002-4541-5114"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyao Li","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-4541-5114","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kangbo Zhao","orcid":"https://orcid.org/0009-0009-7479-7757"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangbo Zhao","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-7479-7757","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130594942","display_name":"Sen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153599","display_name":"Systems, Applications & Products in Data Processing (Australia)","ror":"https://ror.org/04c2m5174","country_code":"AU","type":"company","lineage":["https://openalex.org/I4210132444","https://openalex.org/I4210153599"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sen Zhang","raw_affiliation_strings":["TikTok, ByteDance, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8065-5095","affiliations":[{"raw_affiliation_string":"TikTok, ByteDance, Sydney, Australia","institution_ids":["https://openalex.org/I4210153599"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039893934","display_name":"Yukai Shi","orcid":"https://orcid.org/0000-0002-9413-6528"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yukai Shi","raw_affiliation_strings":["Guangdong University of Technology, Guangzhou, China and University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9413-6528","affiliations":[{"raw_affiliation_string":"Guangdong University of Technology, Guangzhou, China and University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130547048","display_name":"Liang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China and Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5704-4168","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China and Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.39637538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8472999930381775,"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/T11448","display_name":"Face recognition and analysis","score":0.8472999930381775,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1257999986410141,"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/T11094","display_name":"Face Recognition and Perception","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.8716999888420105},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8015000224113464},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.7210999727249146},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6365000009536743},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5913000106811523},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5325000286102295},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.44909998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9007999897003174},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8716999888420105},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8015000224113464},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7210999727249146},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229000091552734},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5325000286102295},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C132900626","wikidata":"https://www.wikidata.org/wiki/Q7534733","display_name":"Sketch recognition","level":4,"score":0.33090001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.28519999980926514}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803012","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3803012","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.767324686050415,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1980093854","https://openalex.org/W2034136097","https://openalex.org/W2563056687","https://openalex.org/W2583409927","https://openalex.org/W2626578807","https://openalex.org/W2765758918","https://openalex.org/W2772330423","https://openalex.org/W2801271986","https://openalex.org/W2890077417","https://openalex.org/W2914578055","https://openalex.org/W2946220758","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963779280","https://openalex.org/W2969985801","https://openalex.org/W3130295820","https://openalex.org/W3139322497","https://openalex.org/W3212516020","https://openalex.org/W3216503469","https://openalex.org/W4220692384","https://openalex.org/W4285414583","https://openalex.org/W4312740349","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4323338350","https://openalex.org/W4361271773","https://openalex.org/W4385527149","https://openalex.org/W4386057725","https://openalex.org/W4386076112","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4386113271","https://openalex.org/W4390874199","https://openalex.org/W4392909601","https://openalex.org/W4399206757","https://openalex.org/W4399310923","https://openalex.org/W4400850951","https://openalex.org/W4402753860","https://openalex.org/W4402754208","https://openalex.org/W4406272807","https://openalex.org/W4406325054","https://openalex.org/W7133242526"],"related_works":[],"abstract_inverted_index":{"Face":[0,119],"sketch":[1,15,69],"synthesis":[2,16,70],"is":[3],"a":[4,66,81,114,151,191],"technique":[5],"aimed":[6],"at":[7,164],"converting":[8],"face":[9,14,39,68,85,130],"photos":[10,139,183],"into":[11,184],"sketches.":[12],"Existing":[13],"research":[17],"mainly":[18],"relies":[19],"on":[20,73,80],"training":[21,52,163],"with":[22,135,140,167],"numerous":[23],"photo\u2013sketch":[24,86,131],"sample":[25],"pairs":[26,128],"from":[27],"existing":[28],"datasets.":[29],"However,":[30],"these":[31],"large-scale":[32],"discriminative":[33],"learning":[34],"methods":[35],"will":[36,208],"have":[37],"to":[38,195],"problems,":[40],"such":[41],"as":[42],"data":[43,53],"scarcity":[44],"and":[45,106,138,147,186,203],"high":[46],"human":[47],"labor":[48],"costs.":[49],"Once":[50],"the":[51,90,168,177],"become":[54],"scarce,":[55],"their":[56],"generative":[57],"performance":[58],"significantly":[59],"degrades.":[60],"In":[61],"this":[62],"article,":[63],"we":[64,112,155],"propose":[65],"one-shot":[67,192],"method":[71,108,179],"based":[72],"diffusion":[74,82],"models.":[75],"We":[76],"optimize":[77],"text":[78],"instructions":[79,91],"model":[83],"using":[84],"image":[87],"pairs.":[88],"Then,":[89],"derived":[92],"through":[93],"gradient-based":[94],"optimization":[95],"are":[96],"used":[97,170],"for":[98,162,171],"inference.":[99,172],"To":[100],"simulate":[101],"real-world":[102],"scenarios":[103],"more":[104,110],"accurately":[105],"evaluate":[107],"effectiveness":[109],"comprehensively,":[111],"introduce":[113],"new":[115],"benchmark":[116,124],"named":[117],"One-shot":[118],"Sketch":[120],"Dataset":[121],"(OS-Sketch).":[122],"The":[123,206],"consists":[125],"of":[126,129,160],"400":[127],"images,":[132],"including":[133],"sketches":[134,189],"different":[136,141],"styles":[137],"backgrounds,":[142],"ages,":[143],"sexes,":[144],"expressions,":[145],"illumination,":[146],"so":[148],"on.":[149],"For":[150],"solid":[152],"out-of-distribution":[153],"evaluation,":[154],"select":[156],"only":[157],"one":[158],"pair":[159],"images":[161],"each":[165],"time,":[166],"rest":[169],"Extensive":[173],"experiments":[174],"demonstrate":[175],"that":[176],"proposed":[178],"can":[180],"convert":[181],"various":[182],"realistic":[185],"highly":[187],"consistent":[188],"in":[190],"context.":[193],"Compared":[194],"other":[196],"methods,":[197],"our":[198],"approach":[199],"offers":[200],"greater":[201],"convenience":[202],"broader":[204],"applicability.":[205],"dataset":[207],"be":[209],"available":[210],"at:":[211],"https://github.com/HanWu3125/OS-Sketch":[212],".":[213]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-26T00:00:00"}