{"id":"W4307715697","doi":"10.1038/s42256-022-00547-8","title":"A fast blind zero-shot denoiser","year":2022,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Krembil Foundation; Government of Canada; Government of Ontario; Canadian Institutes of Health Research; Ontario Genomics; Genome Canada","keywords":"Upsampling; Computer science; Artificial intelligence; Noise reduction; Image (mathematics); Flexibility (engineering); Noise (video); Inference; Computer vision; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063035,0.0002348451,0.0002257264,0.000252286,0.000508312,0.0002123612,0.002489181,0.0001224343,0.0004372502],"category_scores_gemma":[0.0001801657,0.0002161026,0.0001412319,0.001212725,0.00005345986,0.0003175575,0.001171713,0.001862339,0.0001041641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009077053,"about_ca_system_score_gemma":0.0001044712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005762905,"about_ca_topic_score_gemma":0.000006720419,"domain_scores_codex":[0.9975294,0.000351686,0.000309016,0.0006356913,0.0007546567,0.0004195394],"domain_scores_gemma":[0.9985634,0.0002548504,0.0001118799,0.0008297268,0.0001161531,0.0001239609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002977571,0.0004351343,0.0004957019,0.00003700919,0.00007999236,0.000813525,0.002815984,0.01047393,0.01222229,0.1607715,0.01193075,0.7996264],"study_design_scores_gemma":[0.001567118,0.001165708,0.001003003,0.00005721142,0.00006489219,0.001822491,0.0002078323,0.2860717,0.1959409,0.2090085,0.3007597,0.002330915],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001675171,0.003081701,0.983405,0.001413631,0.001503836,0.0001911274,0.00001151859,0.0002164207,0.008501581],"genre_scores_gemma":[0.8965497,0.00002163735,0.09571145,0.004284029,0.0001247395,0.00003656242,0.00001004096,0.00002319358,0.003238636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8948745,"threshold_uncertainty_score":0.881241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02215082026836738,"score_gpt":0.3177002172427404,"score_spread":0.295549396974373,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}