{"id":"W4226263340","doi":"10.1109/access.2022.3140466","title":"Learning Super-Resolution of Environment Matting of Transparent Objects From a Single Image","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Computer science; Computer vision; Image resolution; Resolution (logic); Artificial intelligence","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":[0.0002069452,0.0001076241,0.0001904069,0.0001001849,0.0001518728,0.00005240236,0.001130381,0.00002116706,0.00004527444],"category_scores_gemma":[0.00002583552,0.0001202544,0.00005314281,0.000235486,0.00006768655,0.0008700539,0.0004622109,0.0001883399,0.000001311145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001017303,"about_ca_system_score_gemma":0.00003145189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001264231,"about_ca_topic_score_gemma":0.000002342022,"domain_scores_codex":[0.9986855,0.000111547,0.0003086273,0.0003165262,0.0003910505,0.0001867771],"domain_scores_gemma":[0.9992422,0.00008333562,0.0002665178,0.0003442538,0.00003348078,0.00003018923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001543859,0.0002070544,0.001008222,0.00005253962,0.000011417,0.000008889134,0.002773101,0.01034791,0.9612911,0.00003929289,0.00004751945,0.02419748],"study_design_scores_gemma":[0.0002546221,0.0002141403,0.0007900664,0.00006135785,0.00001173211,0.000004446706,0.0001426017,0.09971227,0.8932338,0.005173009,0.0002180273,0.0001839532],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1564347,0.0002013557,0.8427646,0.0000792719,0.00008883666,0.0001045018,0.00000874579,0.0001371681,0.0001807292],"genre_scores_gemma":[0.7614269,0.00000952852,0.2384677,0.00002518753,0.00001300124,0.00002936506,0.000004039117,0.00001038441,0.00001395672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6049921,"threshold_uncertainty_score":0.4903832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03720674749194872,"score_gpt":0.2863705385783093,"score_spread":0.2491637910863606,"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."}}