{"id":"W2963882477","doi":"10.1109/iccv.2017.484","title":"Learning High Dynamic Range from Outdoor Panoramas","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":108,"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":"High dynamic range; Computer science; Autoencoder; Artificial intelligence; Ranging; Computer vision; Dynamic range; Ground truth; Range (aeronautics); Set (abstract data type); Process (computing); Deep learning; High-dynamic-range imaging; Computer graphics (images); Engineering","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003567192,0.0003883955,0.0004557979,0.0001418691,0.0002391564,0.00133756,0.004188658,0.0003373129,0.0002006686],"category_scores_gemma":[0.0001142936,0.0003682387,0.0001585787,0.00004914007,0.00007025638,0.0004912295,0.005877619,0.001077771,0.0004174058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001548491,"about_ca_system_score_gemma":0.0001274572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002093079,"about_ca_topic_score_gemma":0.00008364053,"domain_scores_codex":[0.9976047,0.0001231156,0.0003297472,0.001091486,0.0004536851,0.0003972489],"domain_scores_gemma":[0.9966286,0.00007811051,0.0004370941,0.002648077,0.0001261668,0.00008198871],"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":[0.00002719011,0.0002957596,0.003767057,0.0002567932,0.0004151779,0.0003994981,0.002719738,0.0003761738,0.008141142,0.0161897,0.01943549,0.9479763],"study_design_scores_gemma":[0.001887721,0.0004629355,0.03244385,0.001633689,0.0001675957,0.0000103226,0.00006772568,0.5709695,0.06001157,0.2841785,0.04289297,0.005273594],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01247726,0.0002009341,0.9686083,0.001268404,0.001585694,0.0004320389,0.00001030426,0.002452767,0.01296432],"genre_scores_gemma":[0.6413248,0.0001228757,0.3445467,0.0001701965,0.0001305238,0.00009487932,0.00006584676,0.00003042448,0.01351373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9427027,"threshold_uncertainty_score":0.999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01590214354332634,"score_gpt":0.2780582301056642,"score_spread":0.2621560865623379,"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."}}