{"id":"W2605060370","doi":"10.1145/3130800.3130891","title":"Learning to predict indoor illumination from a single image","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":332,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Artificial intelligence; Computer vision; High dynamic range; Classifier (UML); High-dynamic-range imaging; Artificial neural network; Light field; Deep learning; Range (aeronautics); Image-based lighting; Global illumination; Deep neural networks; Field (mathematics); Computer graphics (images); Image (mathematics); Image processing; Dynamic range; Rendering (computer graphics); 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":[0.0002148551,0.0001444642,0.0001213091,0.0002646426,0.0008273912,0.0004943906,0.001643998,0.00008284741,0.00002709608],"category_scores_gemma":[0.0002008458,0.0001549979,0.00008191127,0.0002406971,0.00008997782,0.001183078,0.0000479802,0.000329459,0.00006137475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004803718,"about_ca_system_score_gemma":0.00002479151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001224783,"about_ca_topic_score_gemma":0.0000751226,"domain_scores_codex":[0.9988195,0.00005337561,0.000174069,0.0004001583,0.0003281878,0.0002247259],"domain_scores_gemma":[0.9980262,0.0001068572,0.000113957,0.001541911,0.0001254651,0.00008559759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003925644,0.0006341769,0.0007111858,0.00001716479,0.00008696871,0.00003345604,0.003602884,0.00008831921,0.1166951,0.001533947,0.000893022,0.8756645],"study_design_scores_gemma":[0.001128214,0.001774291,0.02349459,0.0002601155,0.00006510109,0.000008873448,0.0001764472,0.02320475,0.9124533,0.02362695,0.01284732,0.0009600635],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03980954,0.000005919133,0.9553667,0.002880489,0.0003092848,0.0002307469,0.000009543455,0.000564902,0.0008228353],"genre_scores_gemma":[0.8084962,0.00002294196,0.1908595,0.0003050601,0.00003183028,0.00006090297,0.000003563748,0.00001382498,0.0002061413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8747045,"threshold_uncertainty_score":0.6363708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0204952666595602,"score_gpt":0.2708492451633954,"score_spread":0.2503539785038352,"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."}}