{"id":"https://openalex.org/W7131283387","doi":"https://doi.org/10.1109/access.2026.3667789","title":"E2Diff: An Efficient Enhanced Diffusion Model for Blind Face Restoration","display_name":"E2Diff: An Efficient Enhanced Diffusion Model for Blind Face Restoration","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131283387","doi":"https://doi.org/10.1109/access.2026.3667789"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3667789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667789","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.2026.3667789","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126688977","display_name":"Rong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I165225704","display_name":"Xizang Minzu University","ror":"https://ror.org/042170a43","country_code":"CN","type":"education","lineage":["https://openalex.org/I165225704"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["Xizang Minzu University, Xianyang, China"],"raw_orcid":"https://orcid.org/0000-0003-3027-2368","affiliations":[{"raw_affiliation_string":"Xizang Minzu University, Xianyang, China","institution_ids":["https://openalex.org/I165225704"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Wang","orcid":"https://orcid.org/0009-0009-9384-3413"},"institutions":[{"id":"https://openalex.org/I4210146584","display_name":"Henan Forestry Vocational College","ror":"https://ror.org/050g87e49","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210146584"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Henan Vocational University of Science and Technology, Zhoukou, China"],"raw_orcid":"https://orcid.org/0009-0009-9384-3413","affiliations":[{"raw_affiliation_string":"Henan Vocational University of Science and Technology, Zhoukou, China","institution_ids":["https://openalex.org/I4210146584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057420493","display_name":"Gencheng Wang","orcid":"https://orcid.org/0009-0009-1369-7939"},"institutions":[{"id":"https://openalex.org/I165225704","display_name":"Xizang Minzu University","ror":"https://ror.org/042170a43","country_code":"CN","type":"education","lineage":["https://openalex.org/I165225704"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gencheng Wang","raw_affiliation_strings":["Xizang Minzu University, Xianyang, China"],"raw_orcid":"https://orcid.org/0009-0009-1369-7939","affiliations":[{"raw_affiliation_string":"Xizang Minzu University, Xianyang, China","institution_ids":["https://openalex.org/I165225704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123772829","display_name":"Daqin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165225704","display_name":"Xizang Minzu University","ror":"https://ror.org/042170a43","country_code":"CN","type":"education","lineage":["https://openalex.org/I165225704"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daqin Li","raw_affiliation_strings":["Xizang Minzu University, Xianyang, China"],"raw_orcid":"https://orcid.org/0009-0008-0281-1233","affiliations":[{"raw_affiliation_string":"Xizang Minzu University, Xianyang, China","institution_ids":["https://openalex.org/I165225704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.17821914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"31286","last_page":"31299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.47929999232292175,"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":0.47929999232292175,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.20720000565052032,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09790000319480896,"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/face","display_name":"Face (sociological concept)","score":0.6065000295639038},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5751000046730042},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5382000207901001},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.447299987077713},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.444599986076355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3684999942779541},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3571000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137000203132629},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723000168800354},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.444599986076355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2971000075340271},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3667789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667789","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"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3667789","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667789","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":[{"score":0.5039637088775635,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5668617214","display_name":null,"funder_award_id":"LSKJ202457","funder_id":"https://openalex.org/F4320309617","funder_display_name":"National Foundation for Science and Technology Development"}],"funders":[{"id":"https://openalex.org/F4320309617","display_name":"National Foundation for Science and Technology Development","ror":"https://ror.org/04rw64z44"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Blind":[0],"face":[1,43,95,137],"restoration":[2,196],"(BFR)":[3],"is":[4,62,74,104,121,212],"crucial":[5],"to":[6,86,92],"improve":[7,93],"the":[8,42,79,87,107,115,128,171],"quality":[9],"of":[10,81,109,186],"low-quality":[11],"facial":[12,99],"images.":[13],"Although":[14],"diffusion":[15,57,102,116,154],"model-based":[16],"methods":[17],"achieve":[18],"reliable":[19],"performance":[20],"in":[21,38,41,156],"BFR":[22,208],"tasks,":[23],"particularly":[24],"under":[25],"unknown":[26],"and":[27,153,159,166,198],"complex":[28],"degradation,":[29],"they":[30],"suffer":[31],"from":[32],"high":[33,47],"computational":[34],"complexity,":[35],"which":[36,76,125],"results":[37,185],"unrealistic":[39],"details":[40],"images":[44],"generated":[45],"at":[46,214],"frequencies.":[48],"To":[49],"address":[50],"these":[51],"limitations,":[52],"a":[53,65,70,101,110,203],"new":[54,66],"efficient":[55],"enhanced":[56],"network,":[58],"known":[59],"as":[60],"E2Diff,":[61,124],"proposed.":[63],"Firstly,":[64],"denoising":[67],"generator":[68],"with":[69],"lightweight":[71],"residual":[72],"module":[73],"introduced,":[75],"considerably":[77],"reduces":[78],"number":[80],"parameters":[82],"by":[83],"40%":[84],"compared":[85],"standard":[88],"U-Net":[89],"model.":[90],"Secondly,":[91],"high-frequency":[94,111],"features":[96],"while":[97,169],"maintaining":[98],"structures,":[100],"framework":[103],"incorporated":[105],"into":[106,123],"design":[108],"feature-generating":[112],"module.":[113],"Lastly,":[114],"probability":[117],"model":[118,129],"(DPM)":[119],"solver":[120],"integrated":[122],"significantly":[126],"increases":[127],"sampling":[130],"frequency.":[131],"Extensive":[132],"evaluations":[133],"on":[134,148],"severely":[135],"degraded":[136],"datasets":[138],"have":[139],"revealed":[140,189],"that":[141,190],"E2Diff":[142,162,191],"outperforms":[143],"current":[144],"state-of-the-art":[145],"approaches":[146],"based":[147],"generative":[149],"adversarial":[150],"networks,":[151],"Transformers,":[152],"models":[155],"both":[157],"qualitative":[158],"quantitative":[160],"terms.":[161],"achieves":[163],"competitive":[164],"PSNR":[165],"SSIM":[167],"scores":[168],"obtaining":[170],"best":[172],"perceptual":[173],"metrics":[174],"(LMD":[175],"=":[176,179,182],"5.91,":[177],"FID-G":[178],"16.62,":[180],"FID-F":[181],"39.87).":[183],"The":[184,210],"this":[187],"study":[188],"effectively":[192],"combines":[193],"visual":[194],"realism,":[195],"integrity,":[197],"computing":[199],"efficiency,":[200],"thereby":[201],"providing":[202],"viable":[204],"solution":[205],"for":[206],"real-world":[207],"applications.":[209],"code":[211],"available":[213],"https://github.com/windcr/E2Diff.":[215]},"counts_by_year":[],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2026-02-25T00:00:00"}