{"id":"W4402916301","doi":"10.1109/cvprw63382.2024.00623","title":"BigEPIT: Scaling EPIT for Light Field Image Super-Resolution","year":2024,"lang":"en","type":"article","venue":"","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Research and Development","keywords":"Scaling; Computer science; Light field; Field (mathematics); Resolution (logic); Image (mathematics); Superresolution; Artificial intelligence; Computer vision; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001196581,0.001239815,0.0009256291,0.0006643153,0.0004548751,0.00102373,0.002077074,0.0009355271,0.00457607],"category_scores_gemma":[0.004051547,0.000489841,0.0007118376,0.000759663,0.000542969,0.002408819,0.00288758,0.001745386,0.0019178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005376832,"about_ca_system_score_gemma":0.0008113296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002344481,"about_ca_topic_score_gemma":0.005875159,"domain_scores_codex":[0.9993539,0.00009894532,0.00003785533,0.0001354295,0.0003135967,0.0000602077],"domain_scores_gemma":[0.9986781,0.0003657568,0.00009203683,0.0005169571,0.0002669422,0.00008016923],"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":[0.0006213023,0.0003292954,0.003562324,0.0004351814,0.0001805638,0.000466705,0.0002340193,0.08061717,0.1125985,0.01256382,0.04163342,0.7467576],"study_design_scores_gemma":[0.00004567504,0.0001376792,0.0008764617,0.00002481131,0.00002539306,0.0004211638,0.00004322538,0.94906,0.03311729,0.005636004,0.01057495,0.00003739732],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02555428,0.0006737483,0.9590248,0.0003647894,0.0001172319,0.0001932345,0.000722377,0.009278318,0.00407122],"genre_scores_gemma":[0.1404614,0.0004263672,0.8519395,0.0005352501,0.00009488023,0.0002449972,0.002158302,0.001009142,0.003130162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00457607,"threshold_uncertainty_score":0.01530844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005713084787511061,"score_gpt":0.2252257379856099,"score_spread":0.2195126531980988,"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."}}