{"id":"W2963780738","doi":"10.1016/j.cviu.2017.09.003","title":"Haze visibility enhancement: A Survey and quantitative benchmarking","year":2017,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation Singapore; Nvidia","keywords":"Benchmark (surveying); Visibility; Benchmarking; Ground truth; Computer science; Haze; Artificial intelligence; Image (mathematics); Filter (signal processing); Computer vision; Remote sensing; Pattern recognition (psychology); Optics; Geography; Cartography; Physics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001355621,0.0002456627,0.0002872325,0.0001493969,0.001169597,0.002522955,0.0006954586,0.00006000428,0.00001515448],"category_scores_gemma":[0.0001013335,0.0002230403,0.00004273077,0.0001033633,0.0003447,0.002412212,0.001478902,0.0001706126,0.000005693435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001237336,"about_ca_system_score_gemma":0.00002695034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005469729,"about_ca_topic_score_gemma":0.00002989525,"domain_scores_codex":[0.9981296,0.0001732787,0.0002972125,0.0007738272,0.0002776452,0.0003484535],"domain_scores_gemma":[0.9984657,0.0002246001,0.0002478148,0.000835682,0.0000981581,0.0001280963],"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":[0.0002703615,0.0006963214,0.01890614,0.00050725,0.0002368442,0.0002516812,0.008627204,0.000002534575,0.06040416,0.3901282,0.01951293,0.5004563],"study_design_scores_gemma":[0.002336325,0.002376867,0.1099087,0.0007817706,0.00002061213,0.00004784669,0.000201602,0.809834,0.01409313,0.05817929,0.0008062011,0.001413648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02417139,0.0001293677,0.9732412,0.0004973673,0.0003680856,0.0002614639,0.000003005239,0.000147626,0.001180558],"genre_scores_gemma":[0.6917366,0.0001183705,0.3079087,0.0001419819,0.00003558727,0.000003822191,0.000003275172,0.000009241142,0.00004232211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8098315,"threshold_uncertainty_score":0.9985125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08099546624211718,"score_gpt":0.350093309666092,"score_spread":0.2690978434239748,"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."}}