{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002310557,0.0008794084,0.0005804512,0.0006802104,0.0001769823,0.0006118994,0.0009437137,0.0004359405,0.002178835],"category_scores_gemma":[0.0008762705,0.0005248652,0.0006420173,0.0004165664,0.0003009903,0.0009517563,0.0007130498,0.001096831,0.001552332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004819873,"about_ca_system_score_gemma":0.0005261429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003355701,"about_ca_topic_score_gemma":0.009652897,"domain_scores_codex":[0.9997626,0.00002043537,0.000005216958,0.0001148336,0.0000657016,0.00003120154],"domain_scores_gemma":[0.9997572,0.00004429741,0.00003321638,0.00007097091,0.00007609639,0.00001819853],"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":[0.0002784757,0.0002755775,0.005163557,0.000146858,0.0001441948,0.0001140293,0.0001064068,0.254634,0.1070618,0.001997437,0.00700182,0.623076],"study_design_scores_gemma":[0.000008288624,0.00003491439,0.002116168,0.00001104606,0.00001684367,0.00006456896,0.00001431747,0.973435,0.02154561,0.00122199,0.001517819,0.00001346876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0349725,0.0001243613,0.9580426,0.00007229795,0.00004284099,0.00003721103,0.0003098412,0.004462145,0.001936202],"genre_scores_gemma":[0.5041875,0.0003652794,0.4881624,0.0002071103,0.00008264294,0.00009914864,0.001628115,0.0005036158,0.004764114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003355701,"threshold_uncertainty_score":0.007288992,"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."}}