{"id":"W4309710446","doi":"10.1145/3565516.3565524","title":"Assessing Advances in Real Noise Image Denoisers","year":2022,"lang":"en","type":"article","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trinity College","funders":"Trinity College Dublin; Science Foundation Ireland","keywords":"Computer science; Benchmark (surveying); Noise reduction; Noise (video); Gaussian noise; Baseline (sea); Noise measurement; Additive white Gaussian noise; Generator (circuit theory); Artificial intelligence; Image (mathematics); White noise; Computer engineering; Telecommunications; Power (physics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0009318038,0.00009075147,0.0001269101,0.0001648758,0.0002284545,0.0003078649,0.0007219199,0.00001459059,0.000170119],"category_scores_gemma":[0.00003459905,0.00008833218,0.00004323328,0.0006375339,0.00002653807,0.002352422,0.0004513817,0.000195993,0.00001463733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009021072,"about_ca_system_score_gemma":0.00008246532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001219005,"about_ca_topic_score_gemma":0.00001306439,"domain_scores_codex":[0.9986018,0.0003245558,0.0001837342,0.000317349,0.0003078479,0.0002647174],"domain_scores_gemma":[0.9994138,0.0001426118,0.00005050588,0.0003185404,0.00002635785,0.00004821228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005814844,0.0003711543,0.003629745,0.00004582272,0.00001153603,0.0009484042,0.002926551,0.006301777,0.1481117,0.0810307,0.002454242,0.7541102],"study_design_scores_gemma":[0.008247063,0.0008535941,0.06706066,0.00009609513,0.00003131916,0.000558167,0.005555443,0.5556651,0.08049586,0.1255361,0.1526062,0.003294294],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02412312,0.0003579599,0.8398518,0.0004786398,0.0003993556,0.0000814921,4.508507e-7,0.0001671809,0.13454],"genre_scores_gemma":[0.4614075,0.00005939371,0.5355865,0.0006273746,0.00004445168,0.00002896044,0.000001645083,0.00001238923,0.002231787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7508159,"threshold_uncertainty_score":0.3602082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02575254494145882,"score_gpt":0.3383553425394265,"score_spread":0.3126027975979677,"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."}}