{"id":"W2767269772","doi":"10.1109/tip.2017.2771142","title":"Learning-Based Restoration of Backlit Images","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Backlight; Computer vision; Artificial intelligence; Computer science; Image quality; Image (mathematics); Liquid-crystal display","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":[0.0003171495,0.0001522802,0.0001602141,0.0001833568,0.0008383321,0.000618611,0.000827309,0.00005845413,0.0000214279],"category_scores_gemma":[0.00003661664,0.0001560833,0.00007323558,0.0001494745,0.0001907581,0.002384179,0.00000482531,0.0002644402,0.00002323024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005298221,"about_ca_system_score_gemma":0.0001356896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590054,"about_ca_topic_score_gemma":0.000004611066,"domain_scores_codex":[0.9988286,0.00005729654,0.0002566249,0.0003367538,0.0003120927,0.0002086487],"domain_scores_gemma":[0.998594,0.00003937071,0.0003382103,0.0007104329,0.0002724676,0.00004547267],"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":[0.00004342061,0.0003217337,0.00005238495,0.0002331236,0.00001399757,0.00001461313,0.0004999822,0.002688568,0.3692749,0.00004562206,0.0002440563,0.6265677],"study_design_scores_gemma":[0.0002672332,0.0001521652,0.000205815,0.0001515204,0.00001058969,0.000002220664,0.00001324261,0.08438002,0.9143657,0.0001731611,0.0001180702,0.0001602784],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001881014,0.00002724141,0.9950682,0.000509778,0.0001656384,0.0001483476,0.000002176501,0.0003946052,0.00180299],"genre_scores_gemma":[0.8104296,0.000006228258,0.1889798,0.00004893583,0.00001763384,0.00003105866,5.727371e-7,0.00001429111,0.0004719004],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8085486,"threshold_uncertainty_score":0.6447857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01787033282565046,"score_gpt":0.2931462082675908,"score_spread":0.2752758754419403,"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."}}