{"id":"https://openalex.org/W7123348478","doi":"https://doi.org/10.1109/access.2026.3652541","title":"Accelerating Diffusion-Based Denoising Model With Optimized Time Steps","display_name":"Accelerating Diffusion-Based Denoising Model With Optimized Time Steps","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123348478","doi":"https://doi.org/10.1109/access.2026.3652541"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3652541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652541","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.2026.3652541","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122891035","display_name":"Jaehyun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I24214720","display_name":"Hansung University","ror":"https://ror.org/048m9x696","country_code":"KR","type":"education","lineage":["https://openalex.org/I24214720"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaehyun Cho","raw_affiliation_strings":["Department of Artificial Intelligence, Hansung University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0007-9135-1509","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Hansung University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I24214720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122901625","display_name":"Youngjoon Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjoon Yoo","raw_affiliation_strings":["Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-8778-5573","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5122891035"],"corresponding_institution_ids":["https://openalex.org/I24214720"],"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":0.06360965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"6986","last_page":"7004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.7387999892234802,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.7387999892234802,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.05009999871253967,"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":0.042899999767541885,"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/noise-reduction","display_name":"Noise reduction","score":0.6776000261306763},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.61080002784729},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5443999767303467},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4796999990940094},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4277999997138977},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.3955000042915344},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.3896999955177307},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3756999969482422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343999743461609},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6776000261306763},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.61080002784729},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5317999720573425},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46709999442100525},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4214000105857849},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3264999985694885},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.32330000400543213},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C101453961","wikidata":"https://www.wikidata.org/wiki/Q7048948","display_name":"Non-local means","level":4,"score":0.3019999861717224},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C293773","wikidata":"https://www.wikidata.org/wiki/Q7608015","display_name":"Step detection","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3652541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652541","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.2026.3652541","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3652541","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":[{"id":"https://metadata.un.org/sdg/11","score":0.5965726375579834,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G13572568","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G1422410287","display_name":null,"funder_award_id":"RS-2022-II220124","funder_id":"https://openalex.org/F4320321202","funder_display_name":"Chung-Ang University"}],"funders":[{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1912194039","https://openalex.org/W1991111872","https://openalex.org/W2117539524","https://openalex.org/W2121927366","https://openalex.org/W2133665775","https://openalex.org/W2618530766","https://openalex.org/W2748263833","https://openalex.org/W2912435603","https://openalex.org/W2962785568","https://openalex.org/W2963800716","https://openalex.org/W2963866045","https://openalex.org/W3035326127","https://openalex.org/W3096831136","https://openalex.org/W3155072588","https://openalex.org/W3201952986","https://openalex.org/W3204358387","https://openalex.org/W3207918547","https://openalex.org/W3213467918","https://openalex.org/W4225672218","https://openalex.org/W4226014430","https://openalex.org/W4229944339","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4312938066","https://openalex.org/W4317496742","https://openalex.org/W4320013936","https://openalex.org/W4385220848","https://openalex.org/W4385245566","https://openalex.org/W4385800876","https://openalex.org/W4386076002","https://openalex.org/W4386083034","https://openalex.org/W4386938512","https://openalex.org/W4387587622","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390873650","https://openalex.org/W4391547658","https://openalex.org/W4391753194","https://openalex.org/W4393148714","https://openalex.org/W4400905853","https://openalex.org/W4402709450","https://openalex.org/W4402726956","https://openalex.org/W4402727162","https://openalex.org/W4402754171","https://openalex.org/W4403791004","https://openalex.org/W4406814982","https://openalex.org/W4409366120","https://openalex.org/W4409369698","https://openalex.org/W4411528087","https://openalex.org/W4413147532","https://openalex.org/W4414798741","https://openalex.org/W4415796023","https://openalex.org/W4415796372","https://openalex.org/W4415797645","https://openalex.org/W7083575751"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,67,100],"achieve":[2],"state-of-the-art":[3],"performance":[4],"in":[5],"image":[6,33],"denoising":[7,39,66],"but":[8],"are":[9],"hindered":[10],"by":[11,55,141],"a":[12,47,59,83,88,151],"slow,":[13],"iterative":[14],"sampling":[15,129],"process.":[16],"While":[17],"advanced,":[18],"training-free":[19,153],"samplers":[20],"and":[21,57,104,134,144,149],"optimized":[22,111],"schedules":[23],"offer":[24],"significant":[25],"acceleration,":[26],"their":[27],"validation":[28],"has":[29],"been":[30],"focused":[31],"on":[32,43,98],"generation.":[34],"Their":[35],"applicability":[36],"to":[37,124],"pre-trained":[38,65],"models,":[40],"which":[41],"operate":[42],"conditional":[44],"inputs,":[45],"remains":[46],"critical,":[48],"unverified":[49],"gap.":[50],"We":[51,118],"address":[52],"this":[53,80],"gap":[54],"applying":[56],"validating":[58],"post-hoc":[60],"timestep":[61],"optimization":[62],"that":[63,108,120],"accelerates":[64],"without":[68],"retraining.":[69],"By":[70],"minimizing":[71],"the":[72,76,109,115,126],"discretization":[73],"error":[74],"of":[75,91,128],"underlying":[77],"diffusion":[78],"ODE,":[79],"method":[81],"finds":[82],"non-uniform":[84],"optimal":[85],"schedule":[86,112],"for":[87,101,155,163],"given":[89],"number":[90,127],"function":[92],"evaluations":[93],"(NFE).":[94],"Our":[95,166],"extensive":[96],"experiments":[97],"diverse":[99],"real-world,":[102],"weather,":[103],"Gaussian":[105],"noise":[106],"demonstrate":[107,119],"proposed":[110],"effectively":[113],"reduces":[114],"required":[116],"NFE.":[117],"it":[121],"is":[122,168],"possible":[123],"reduce":[125],"steps":[130],"while":[131],"significantly":[132],"preserving,":[133],"often":[135],"improving,":[136],"restoration":[137],"quality":[138],"as":[139],"measured":[140],"PSNR,":[142],"SSIM,":[143],"LPIPS.":[145],"This":[146],"work":[147],"presents":[148],"validates":[150],"practical,":[152],"strategy":[154],"substantially":[156],"accelerating":[157],"diffusion-based":[158],"denoising,":[159],"enhancing":[160],"its":[161],"viability":[162],"real-world":[164],"applications.":[165],"code":[167],"available":[169],"at:":[170],"https://github.com/cv-cho/Accelerating-Diffusion-Denoising-Models.":[171]},"counts_by_year":[],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2026-01-14T00:00:00"}