{"id":"https://openalex.org/W7143525420","doi":"https://doi.org/10.48550/arxiv.2603.25869","title":"Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising","display_name":"Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7143525420","doi":"https://doi.org/10.48550/arxiv.2603.25869"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25869","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007897386","display_name":"Brayan Monroy","orcid":"https://orcid.org/0000-0002-1087-3062"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Monroy, Brayan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090572051","display_name":"Jorge Brandon Fuentes Bacca","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bacca, Jorge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083772205","display_name":"Juli\u00e1n Tachella","orcid":"https://orcid.org/0000-0003-3878-9142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tachella, Juli\u00e1n","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007897386"],"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9513000249862671,"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":0.9513000249862671,"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":0.00570000009611249,"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"}},{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.0044999998062849045,"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","display_name":"Noise (video)","score":0.7458999752998352},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6777999997138977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5271999835968018},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/value-noise","display_name":"Value noise","score":0.45410001277923584},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4348999857902527},{"id":"https://openalex.org/keywords/image-noise","display_name":"Image noise","score":0.42800000309944153},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4242999851703644}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7458999752998352},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6777999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6485000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6216999888420105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C182163834","wikidata":"https://www.wikidata.org/wiki/Q2926529","display_name":"Value noise","level":5,"score":0.45410001277923584},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.42800000309944153},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C200378446","wikidata":"https://www.wikidata.org/wiki/Q4147391","display_name":"Gradient noise","level":5,"score":0.3506999909877777},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.33730000257492065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2702000141143799},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2694000005722046},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25869","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.25869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25869","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6789127588272095}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"image":[1],"denoising":[2,74],"methods":[3],"have":[4],"traditionally":[5],"relied":[6],"on":[7],"either":[8],"architectural":[9],"constraints":[10],"or":[11,35],"specialized":[12],"loss":[13],"functions":[14],"that":[15,76,94],"require":[16,53],"prior":[17],"knowledge":[18,55,81],"of":[19,56,82],"the":[20,25,45,57,78,83,96],"noise":[21,43,58,72,84,114,128],"distribution":[22],"to":[23,44,68],"avoid":[24],"trivial":[26],"identity":[27],"mapping.":[28],"Among":[29],"these,":[30],"approaches":[31,52],"such":[32,116,130],"as":[33,117,124,126,131],"Noisier2Noise":[34],"Recorrupted2Recorrupted,":[36],"create":[37],"training":[38],"pairs":[39],"by":[40],"adding":[41],"synthetic":[42],"noisy":[46],"images.":[47],"While":[48],"effective,":[49],"these":[50],"recorruption-based":[51],"precise":[54],"distribution,":[59],"which":[60],"is":[61],"often":[62],"not":[63],"available.":[64],"We":[65],"present":[66],"Learning":[67],"Recorrupt":[69],"(L2R),":[70],"a":[71,89,100],"distribution-agnostic":[73],"technique":[75],"eliminates":[77],"need":[79],"for":[80],"distribution.":[85],"Our":[86],"method":[87,106],"introduces":[88],"learnable":[90],"monotonic":[91],"neural":[92],"network":[93],"learns":[95],"recorruption":[97],"process":[98],"through":[99],"min-max":[101],"saddle-point":[102],"objective.":[103],"The":[104],"proposed":[105],"achieves":[107],"state-of-the-art":[108],"performance":[109],"across":[110],"unconventional":[111],"and":[112,120],"heavy-tailed":[113],"distributions,":[115],"log-gamma,":[118],"Laplace,":[119],"spatially":[121],"correlated":[122],"noise,":[123],"well":[125],"signal-dependent":[127],"models":[129],"Poisson-Gaussian":[132],"noise.":[133]},"counts_by_year":[],"updated_date":"2026-03-31T06:07:48.031334","created_date":"2026-03-31T00:00:00"}