{"id":"W3157906910","doi":"10.3390/s21092998","title":"Adversarial Gaussian Denoiser for Multiple-Level Image Denoising","year":2021,"lang":"en","type":"article","venue":"Sensors","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Noise reduction; Artificial intelligence; Computer science; Convolutional neural network; Adversarial system; Image (mathematics); Pattern recognition (psychology); Noise (video); Non-local means; Image denoising; Inpainting; Computer vision","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":[0.0004406901,0.0001976258,0.0002520921,0.00009811993,0.0002826106,0.0003612643,0.0004882384,0.0001025386,0.00002524387],"category_scores_gemma":[0.0007985669,0.0001958045,0.0001997954,0.0003669557,0.00005408264,0.0004114189,0.0001930695,0.0001536436,0.00007708028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000543203,"about_ca_system_score_gemma":0.000132885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003114105,"about_ca_topic_score_gemma":0.0000219322,"domain_scores_codex":[0.9981548,0.0002226922,0.0002790294,0.0005696597,0.0002819715,0.0004918639],"domain_scores_gemma":[0.9983316,0.0005369989,0.00008346624,0.0006287821,0.0002773296,0.0001418291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002494349,0.0002582895,0.0003794002,0.0001424947,0.000177605,0.001486251,0.003918737,0.001298543,0.8241519,0.0189626,0.008087055,0.1408876],"study_design_scores_gemma":[0.005293416,0.0001190539,0.003042494,0.00009138972,0.00006759776,0.0002893002,0.0002979619,0.1093426,0.8379521,0.01076842,0.03178219,0.0009534652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04019019,0.0001102571,0.9548147,0.001110237,0.001199463,0.0001882391,0.00001547067,0.0001637928,0.002207632],"genre_scores_gemma":[0.1799698,0.000006196369,0.8150257,0.0006672164,0.0004410954,0.000009061961,0.00001129064,0.00003084688,0.003838709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1399342,"threshold_uncertainty_score":0.7984674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04303237635647333,"score_gpt":0.2963711017674756,"score_spread":0.2533387254110023,"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."}}