{"id":"https://openalex.org/W7125631143","doi":"https://doi.org/10.1109/access.2026.3657027","title":"Pixelated Face Recovery Using Multi-Step Cycle Asymmetric GAN","display_name":"Pixelated Face Recovery Using Multi-Step Cycle Asymmetric GAN","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125631143","doi":"https://doi.org/10.1109/access.2026.3657027"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3657027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3657027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3657027","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033637712","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0002-1332-9724"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Liu","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123787661","display_name":"Cheolkon Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheolkon Jung","raw_affiliation_strings":["School of Electronic Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0299-7206","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08539111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"18442","last_page":"18454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8129000067710876,"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":0.8129000067710876,"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":0.10369999706745148,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.008299999870359898,"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/discriminator","display_name":"Discriminator","score":0.6955999732017517},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5875999927520752},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5349000096321106},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47519999742507935},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47369998693466187},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4717999994754791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270999789237976},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6955999732017517},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.589900016784668},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5349000096321106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4717999994754791},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3657027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3657027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9c136f835ed54dcb9d38f6958d104f31","is_oa":false,"landing_page_url":"https://doaj.org/article/9c136f835ed54dcb9d38f6958d104f31","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 18442-18454 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3657027","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3657027","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.48610538244247437}],"awards":[{"id":"https://openalex.org/G4457358854","display_name":null,"funder_award_id":"62111540272","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2562637781","https://openalex.org/W2765811365","https://openalex.org/W2950689937","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2964101377","https://openalex.org/W2976718572","https://openalex.org/W2995611514","https://openalex.org/W3011005573","https://openalex.org/W3017136408","https://openalex.org/W3034352949","https://openalex.org/W3119391778","https://openalex.org/W3166898278","https://openalex.org/W3167297682","https://openalex.org/W3199532396","https://openalex.org/W4200634144","https://openalex.org/W4214584876","https://openalex.org/W4223961890","https://openalex.org/W4225592316","https://openalex.org/W4297199690","https://openalex.org/W4316126727","https://openalex.org/W4378087065","https://openalex.org/W4385245566","https://openalex.org/W4387368945","https://openalex.org/W4391604206","https://openalex.org/W4392096985","https://openalex.org/W4393252775","https://openalex.org/W4394597120","https://openalex.org/W4395069541","https://openalex.org/W4401634206","https://openalex.org/W4402215982","https://openalex.org/W4403791406","https://openalex.org/W4409906542","https://openalex.org/W4414500108","https://openalex.org/W4414760333"],"related_works":[],"abstract_inverted_index":{"Recovering":[0],"facial":[1,198,208],"identity":[2,57],"from":[3,68,128,200],"severely":[4],"pixelated":[5,33,70,202],"images":[6],"remains":[7],"a":[8,24,49,101],"highly":[9],"ill-posed":[10],"problem":[11],"due":[12],"to":[13,52,89,113,153],"extreme":[14],"information":[15],"loss.":[16],"To":[17,62],"address":[18],"this":[19,21],"challenge,":[20],"paper":[22],"proposes":[23],"multi-step":[25,43,102],"cycle":[26],"asymmetric":[27,40],"generative":[28],"adversarial":[29,181],"network":[30],"(GAN)":[31],"for":[32,78,215],"face":[34,216],"recovery.":[35],"The":[36,163],"proposed":[37,193],"framework":[38],"introduces":[39],"generators,":[41],"progressive":[42],"refinement,":[44],"attention-guided":[45],"feature":[46,171],"learning,":[47],"and":[48,59,94,137,158,177,187,210,224],"U-Net":[50,151],"discriminator":[51],"jointly":[53],"enhance":[54],"reconstruction":[55],"fidelity,":[56],"preservation,":[58],"training":[60,136,161,178],"stability.":[61],"recover":[63],"realistic":[64],"faces":[65,203],"with":[66,124,166,173],"fidelity":[67],"the":[69,116,122,155,160,192,201,207],"ones,":[71],"we":[72,120,149],"adopt":[73,100,150],"multiple":[74,110],"steps":[75],"in":[76,180,185,218],"generator":[77],"hierarchical":[79],"refinement.":[80],"Each":[81],"step":[82],"utilizes":[83],"attention-based":[84],"convolutional":[85],"neural":[86],"networks":[87],"(CNNs)":[88],"capture":[90],"both":[91,221],"global":[92],"context":[93],"local":[95,142],"features":[96],"during":[97],"upscaling.":[98],"We":[99],"generation":[103,117],"strategy":[104],"that":[105,191],"applies":[106],"loss":[107],"constraints":[108],"at":[109],"intermediate":[111],"resolutions":[112],"progressively":[114],"guide":[115],"process.":[118,162],"Moreover,":[119],"initialize":[121],"GAN":[123],"pre-trained":[125],"weights":[126],"obtained":[127],"an":[129],"independently":[130],"trained":[131],"generator,":[132],"which":[133],"helps":[134],"stabilize":[135,159],"reduces":[138],"artifacts":[139],"such":[140],"as":[141],"holes":[143],"or":[144],"structural":[145],"distortions.":[146],"Regarding":[147],"discriminator,":[148],"architecture":[152],"increase":[154],"discriminator’s":[156],"capability":[157],"encoder-decoder":[164],"structure":[165],"skip":[167],"connections":[168],"facilitates":[169],"effective":[170],"extraction":[172],"outstanding":[174],"discrimination":[175],"accuracy":[176],"stability":[179],"networks.":[182],"Experimental":[183],"results":[184],"CelebA-HQ":[186],"FFHQ":[188],"datasets":[189],"show":[190],"method":[194],"effectively":[195],"recovers":[196],"clear":[197],"details":[199],"while":[204],"successfully":[205],"recognizing":[206],"identity,":[209],"outperforms":[211],"state-of-the-art":[212],"(SOTA)":[213],"ones":[214],"depixelation":[217],"terms":[219],"of":[220],"visual":[222],"quality":[223],"quantitative":[225],"measurements.":[226]},"counts_by_year":[],"updated_date":"2026-02-11T14:41:00.668223","created_date":"2026-01-26T00:00:00"}