{"id":"W3022206370","doi":"10.1007/978-3-030-58607-2_7","title":"Defocus Deblurring Using Dual-Pixel Data","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre for Social Innovation; York University","funders":"","keywords":"Deblurring; Artificial intelligence; Computer vision; Computer science; Focus (optics); Aperture (computer memory); Depth of field; Lens (geology); Pixel; Image restoration; Photography; Image (mathematics); Image processing; Optics; Physics","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"],"consensus_categories":[],"category_scores_codex":[0.0003088924,0.0002689197,0.000251496,0.0001961943,0.0001405723,0.0004458561,0.002130446,0.0001537776,0.000002896178],"category_scores_gemma":[0.00007423514,0.0002751744,0.00003299165,0.0008301217,0.000178843,0.0002532825,0.00377088,0.0008393658,0.000004993285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001604377,"about_ca_system_score_gemma":0.0002038923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000353824,"about_ca_topic_score_gemma":0.00001284864,"domain_scores_codex":[0.9981776,0.00001153272,0.0002766353,0.0008668831,0.0002852699,0.0003820718],"domain_scores_gemma":[0.998394,0.00005735508,0.00006088352,0.001339673,0.00005898088,0.00008907889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[5.500387e-7,0.000009363793,0.00004597959,0.0001569411,0.000004544565,0.00001029636,0.0002281868,0.768099,0.01407586,0.00001651828,0.00002120656,0.2173316],"study_design_scores_gemma":[0.0000386998,0.000004366772,0.00003793085,0.0002274617,0.000008315834,0.00002007543,1.610816e-7,0.9700145,0.01433375,0.014895,0.0001216219,0.0002980916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009457042,0.0005702433,0.988122,0.0003386996,0.0005611306,0.0002207223,0.00001929069,0.0006844047,0.00002642315],"genre_scores_gemma":[0.500398,0.0000142843,0.4992082,0.0001267803,0.0002133022,0.000007647582,0.00001142465,0.00002029339,4.799176e-8],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4909409,"threshold_uncertainty_score":0.99997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0560107448646267,"score_gpt":0.3098516503520186,"score_spread":0.2538409054873919,"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."}}