{"id":"W2968317623","doi":"10.1109/iccvw.2019.00060","title":"WhiteNNer-Blind Image Denoising via Noise Whiteness Priors","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Nvidia; California HIV/AIDS Research Program","keywords":"Prior probability; Computer science; Artificial intelligence; Noise reduction; Noise (video); Image quality; Piecewise; Ground truth; Computer vision; Pattern recognition (psychology); Image (mathematics); Mathematics","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00183213,0.0007697291,0.0009408834,0.0006001963,0.0002692705,0.002068485,0.003982796,0.0006369525,0.000115785],"category_scores_gemma":[0.0001535801,0.0006919965,0.0004675467,0.0006396907,0.0001114222,0.00102561,0.005059548,0.001318924,0.0008376626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001738585,"about_ca_system_score_gemma":0.0004241554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002157715,"about_ca_topic_score_gemma":0.00001289624,"domain_scores_codex":[0.9949623,0.0005607604,0.0008219308,0.001857284,0.000886415,0.0009113085],"domain_scores_gemma":[0.9951448,0.000315962,0.0004513921,0.003235192,0.0005733927,0.0002792093],"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":[0.0004639431,0.0009868952,0.001603104,0.002497951,0.0007192229,0.001528533,0.007390182,0.01845106,0.1981028,0.009644854,0.0126977,0.7459137],"study_design_scores_gemma":[0.009532397,0.000491622,0.008923565,0.002139658,0.0004710704,0.0006691631,0.0002036686,0.7018503,0.1669559,0.08282699,0.01656686,0.009368858],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01109842,0.0006013776,0.9642486,0.0009583872,0.003712007,0.0007363585,0.000005643888,0.0006344881,0.01800472],"genre_scores_gemma":[0.1106752,0.0000699539,0.8786528,0.001196939,0.0005339531,0.00004035105,0.00003169366,0.0001100182,0.008689118],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7365448,"threshold_uncertainty_score":0.9999403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02739071707556231,"score_gpt":0.2969964866385652,"score_spread":0.2696057695630029,"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."}}