{"id":"W4385377051","doi":"10.1007/978-981-99-4742-3_21","title":"Improved Blind Image Denoising with DnCNN","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Noise reduction; Gaussian noise; Additive white Gaussian noise; Artificial intelligence; Noise (video); Image denoising; Pattern recognition (psychology); White noise; Convolutional neural network; Image (mathematics); Video denoising; Computer vision; Video processing; Telecommunications","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"],"consensus_categories":[],"category_scores_codex":[0.001822235,0.0006966575,0.0006811707,0.001225676,0.0004161022,0.001595407,0.003875053,0.0003364119,0.00001126725],"category_scores_gemma":[0.0001537156,0.0005710461,0.0001497555,0.001348044,0.0009051288,0.001111298,0.00154783,0.001164203,0.0001108018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002416439,"about_ca_system_score_gemma":0.0008166641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000038093,"about_ca_topic_score_gemma":0.00006434954,"domain_scores_codex":[0.9951514,0.00007453693,0.0005517655,0.002029691,0.00119193,0.001000679],"domain_scores_gemma":[0.9963877,0.0007922996,0.0003259377,0.001831755,0.0004272634,0.00023505],"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":[0.00005870337,0.00004707347,0.000009774762,0.00008804914,0.00003378345,0.001043082,0.001058345,0.004566956,0.007731193,0.006589632,0.00004329566,0.9787301],"study_design_scores_gemma":[0.00281348,0.001116108,0.00009892435,0.00136314,0.00004357634,0.0004866849,4.911308e-7,0.7371274,0.02438414,0.2292067,0.0009662071,0.002393169],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008126073,0.0001816919,0.9933008,0.0005939922,0.001542013,0.0004192558,0.000003411088,0.0004382711,0.003439313],"genre_scores_gemma":[0.006886696,0.00002620262,0.9882584,0.001298015,0.0006143906,0.000009732764,0.000004683498,0.00009806309,0.002803816],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.976337,"threshold_uncertainty_score":0.9996741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02482658428134378,"score_gpt":0.275006093840272,"score_spread":0.2501795095589283,"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."}}