{"id":"W2737368828","doi":"10.1145/3072959.3073601","title":"Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":308,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; McGill University","keywords":"Computer science; Rendering (computer graphics); Monte Carlo method; Artificial intelligence; Pixel; Deep learning; Global illumination; Noise reduction; Computer vision; Autoencoder; Iterative reconstruction; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001719087,0.0001547639,0.0001882342,0.0002939349,0.0007881981,0.0002284347,0.0009319039,0.00005474594,0.000009756702],"category_scores_gemma":[0.00009980082,0.0001494014,0.0001448468,0.0002363232,0.0002603048,0.002357469,0.00003240753,0.0003392442,0.000002830415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000609891,"about_ca_system_score_gemma":0.00007169075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001597587,"about_ca_topic_score_gemma":0.00006382753,"domain_scores_codex":[0.9988487,0.00006013802,0.0002827245,0.0003651482,0.0002395622,0.0002037723],"domain_scores_gemma":[0.9981567,0.0001040691,0.0003296661,0.001123415,0.0002137798,0.00007236696],"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":[0.00005119059,0.0001666708,0.0005851474,0.00003571443,0.00008686903,0.00001484997,0.001801471,0.003203811,0.0139746,0.001057765,0.00001074506,0.9790112],"study_design_scores_gemma":[0.0006782766,0.0002143106,0.003134703,0.0007041847,0.00005683589,0.0001906546,0.0004973342,0.9402527,0.03458991,0.01902002,0.0001951699,0.0004658612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05307014,0.00005805978,0.944913,0.0006088581,0.001017239,0.0001133554,0.000008292193,0.00007633914,0.0001346864],"genre_scores_gemma":[0.7041039,0.0001215806,0.2956766,0.00005748957,0.00001488715,0.000004261444,1.683666e-7,0.000008262115,0.00001292862],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9785453,"threshold_uncertainty_score":0.6092411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04336275536813264,"score_gpt":0.3371669764392153,"score_spread":0.2938042210710826,"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."}}