{"id":"W7110006137","doi":"10.1145/3757377.3763931","title":"Nonlinear Noise2Noise for Efficient Monte Carlo Denoiser Training","year":2025,"lang":"","type":"article","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Nonlinear system; Preprocessor; Skew; Noise (video); Monte Carlo method; Noise measurement; Training (meteorology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002222478,0.0008560213,0.0007415748,0.0006562796,0.0005308684,0.0009024694,0.001294469,0.001787936,0.004952667],"category_scores_gemma":[0.01025441,0.0005814302,0.0006780089,0.0006372732,0.001076739,0.0009159863,0.001575058,0.001999647,0.00177908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007216188,"about_ca_system_score_gemma":0.001179131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003018103,"about_ca_topic_score_gemma":0.006002574,"domain_scores_codex":[0.9992117,0.0003062288,0.00003273554,0.00009565015,0.0002976425,0.00005605304],"domain_scores_gemma":[0.9975584,0.001737959,0.0001201716,0.0002352016,0.0002917547,0.00005649975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002222069,0.00007900877,0.0008571002,0.0002172867,0.00007249921,0.0001550619,0.0001614764,0.7426763,0.01345362,0.128342,0.004731033,0.1090324],"study_design_scores_gemma":[0.000005326042,0.000009633883,0.00005064062,0.000009840434,0.000002842859,0.00002437176,0.000004053864,0.9848873,0.002072294,0.01131471,0.001612337,0.000006574589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001413075,0.0000948249,0.997122,0.00007130649,0.00001748624,0.00001786851,0.0000240874,0.0002307985,0.00100845],"genre_scores_gemma":[0.109093,0.0002910538,0.8832327,0.0002391896,0.00007484567,0.0002868748,0.0002955119,0.0004551806,0.006031641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004952667,"threshold_uncertainty_score":0.0165683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03924644366268163,"score_gpt":0.3186880635187004,"score_spread":0.2794416198560187,"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."}}