{"id":"https://openalex.org/W7140209584","doi":"https://doi.org/10.48550/arxiv.2603.21045","title":"LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction","display_name":"LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction","publication_year":2026,"publication_date":"2026-03-22","ids":{"openalex":"https://openalex.org/W7140209584","doi":"https://doi.org/10.48550/arxiv.2603.21045"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21045","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huang, Shuwei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Shizhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shizhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wei, Zijun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9603999853134155,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9603999853134155,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.007699999958276749,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5038999915122986},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.48010000586509705},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4781999886035919},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4088999927043915},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.3790999948978424},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.3736000061035156},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.373199999332428},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.3621000051498413}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6129999756813049},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6032000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5422999858856201},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3736000061035156},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3619999885559082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35519999265670776},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C30684385","wikidata":"https://www.wikidata.org/wiki/Q176509","display_name":"Ringing","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21045","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21045","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"image":[1],"super-resolution":[2],"(SR)":[3],"aims":[4],"to":[5,31,62,124],"reconstruct":[6],"high-resolution":[7],"(HR)":[8],"images":[9],"from":[10,90],"low-resolution":[11],"(LR)":[12],"observations.":[13],"However,":[14],"the":[15,20,25,40,59,79,112,148],"inherent":[16],"randomness":[17],"injected":[18],"during":[19],"reverse":[21,150],"diffusion":[22,67,88,105,114,159],"process":[23],"causes":[24],"performance":[26,169],"of":[27,49,147,186],"diffusion-based":[28],"SR":[29],"models":[30,89],"vary":[32],"significantly":[33],"across":[34,104],"different":[35],"sampling":[36,41],"runs,":[37],"particularly":[38],"when":[39],"trajectory":[42,142],"is":[43,58,153],"compressed":[44],"into":[45],"a":[46,74,91,97,135],"limited":[47],"number":[48],"steps.":[50],"A":[51],"critical":[52],"yet":[53],"underexplored":[54],"question":[55],"is:":[56],"what":[57],"optimal":[60,84],"noise":[61,86,122],"inject":[63],"at":[64,192],"each":[65],"intermediate":[66,85],"step?":[68],"In":[69],"this":[70,109],"paper,":[71],"we":[72],"establish":[73],"theoretical":[75],"framework":[76,110],"that":[77,102,164],"derives":[78],"closed-form":[80],"analytical":[81],"solution":[82],"for":[83,156],"in":[87],"maximum":[92],"likelihood":[93],"estimation":[94],"perspective,":[95],"revealing":[96],"consistent":[98],"conditional":[99],"dependence":[100],"structure":[101],"generalizes":[103],"paradigms.":[106],"We":[107,129],"instantiate":[108],"under":[111],"residual-shifting":[113],"paradigm":[115],"and":[116,173],"accordingly":[117],"design":[118],"an":[119],"LR-guided":[120],"multi-input-aware":[121],"predictor":[123],"replace":[125],"random":[126],"Gaussian":[127],"noise.":[128],"further":[130],"mitigate":[131],"initialization":[132],"bias":[133],"with":[134],"high-quality":[136],"pre-upsampling":[137],"network.":[138],"The":[139,183],"compact":[140],"4-step":[141],"uniquely":[143],"enables":[144],"end-to-end":[145],"optimization":[146],"entire":[149],"chain,":[151],"which":[152],"computationally":[154],"prohibitive":[155],"conventional":[157],"long-trajectory":[158],"models.":[160],"Extensive":[161],"experiments":[162],"demonstrate":[163],"LPNSR":[165],"achieves":[166],"state-of-the-art":[167],"perceptual":[168],"on":[170,178],"both":[171],"synthetic":[172],"real-world":[174],"datasets,":[175],"without":[176],"relying":[177],"any":[179],"large-scale":[180],"text-to-image":[181],"priors.":[182],"source":[184],"code":[185],"our":[187],"method":[188],"can":[189],"be":[190],"found":[191],"https://github.com/Faze-Hsw/LPNSR.":[193]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}