{"id":"W4386076237","doi":"10.1109/cvpr52729.2023.01752","title":"GamutMLP: A Lightweight MLP for Color Loss Recovery","year":2023,"lang":"en","type":"article","venue":"","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gamut; Computer science; Artificial intelligence; RGB color model; Color space; Computer vision; RGB color space; Lightness; Color depth; Color balance; Color constancy; Clipping (morphology); Color management; Computer graphics (images); Color image; Image processing; Image (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":[0.0003374376,0.0001095656,0.0001243524,0.0001511117,0.00009191394,0.0001419929,0.0007590377,0.00005174637,0.00005351923],"category_scores_gemma":[0.00005596113,0.00009388143,0.00007636956,0.0005677198,0.00002307452,0.0005500447,0.0002835099,0.00004937682,0.0005696161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004283109,"about_ca_system_score_gemma":0.00004661604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006126044,"about_ca_topic_score_gemma":0.000005298337,"domain_scores_codex":[0.9989361,0.00001817269,0.0001731172,0.0003501829,0.0001783584,0.0003440993],"domain_scores_gemma":[0.9991906,0.0001521608,0.00004566671,0.0004826942,0.00008013093,0.00004875978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001572472,0.00005836483,0.00006166247,0.00003782504,0.00002365006,0.00003649716,0.0001696666,0.000005526008,0.01204352,0.1359267,0.8131276,0.03849323],"study_design_scores_gemma":[0.0004471084,0.0004632902,0.0003241143,0.00003270519,0.00000628129,0.000008885228,0.00001233382,0.04197852,0.5967291,0.03928592,0.320299,0.0004127366],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003193305,0.00001702069,0.9768669,0.003119645,0.0004755513,0.0004708187,0.000003482342,0.002477609,0.01337564],"genre_scores_gemma":[0.1041249,0.0001073659,0.7975116,0.002865474,0.0002799169,0.0008727454,0.00001880057,0.00004002863,0.09417912],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5846856,"threshold_uncertainty_score":0.7321453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0182752534558556,"score_gpt":0.2757420893765767,"score_spread":0.2574668359207211,"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."}}