{"id":"W3036992002","doi":"10.1109/tpami.2021.3070580","title":"CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks","year":2021,"lang":"en","type":"preprint","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Deblurring; Artificial intelligence; Computer vision; Computer science; RGB color model; Pipeline (software); Color balance; Image (mathematics); Image processing; Color image; Image restoration","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004591572,0.000583158,0.0008011374,0.0008392664,0.0003508466,0.001191256,0.001154513,0.0002469938,0.00009006223],"category_scores_gemma":[0.000005865518,0.0005539897,0.0006896495,0.0008904077,0.0001090925,0.0004749956,0.00008820726,0.000754818,0.00000728004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009629231,"about_ca_system_score_gemma":0.00008545481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006591664,"about_ca_topic_score_gemma":0.0003779453,"domain_scores_codex":[0.9966395,0.000128882,0.0007724409,0.001542706,0.0004805475,0.0004358677],"domain_scores_gemma":[0.9977348,0.0002065022,0.000354329,0.001197316,0.0003573269,0.0001497265],"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":[0.00000966581,0.0002563915,0.00002084119,0.0002274884,0.0005627256,0.00001889761,0.0002861515,0.03053917,0.000996445,0.000006813654,0.00007654978,0.9669989],"study_design_scores_gemma":[0.00009357125,0.0001582492,0.0002037459,0.000368059,0.0005794165,0.000009112322,0.00001971592,0.6093196,0.3882012,0.0003749565,0.00005703342,0.0006153596],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008233414,0.0003478546,0.9966221,0.0005546521,0.0006706236,0.0004602735,0.0001825824,0.0003035249,0.00003498226],"genre_scores_gemma":[0.8446811,0.001010087,0.1530068,0.0007570883,0.00007616862,0.0001553938,0.00008385394,0.00003429145,0.0001951395],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9663835,"threshold_uncertainty_score":0.9998456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02800213758311258,"score_gpt":0.3091674943831509,"score_spread":0.2811653568000383,"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."}}