{"id":"W3167532259","doi":"10.48550/arxiv.2106.06629","title":"Mirror3D: Depth Refinement for Mirror Surfaces","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Context (archaeology); Depth map; Artificial intelligence; Plane (geometry); Key (lock); RGB color model; Surface (topology); Computer vision; Plane mirror; Optics; Mathematics; Geology; Geometry; Physics; Image (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":[0.0008422117,0.003686889,0.001592751,0.001749659,0.0005966534,0.001552537,0.003609479,0.001495139,0.008005584],"category_scores_gemma":[0.003909261,0.001077391,0.002238675,0.001256875,0.0006488826,0.001844052,0.002991607,0.002343056,0.007209241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008459682,"about_ca_system_score_gemma":0.001551371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01405891,"about_ca_topic_score_gemma":0.04179522,"domain_scores_codex":[0.998569,0.0001270919,0.00006154874,0.0005408399,0.0005623057,0.0001391738],"domain_scores_gemma":[0.9990921,0.0001410952,0.00008085185,0.0004454785,0.0001933778,0.00004701407],"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":[0.001140505,0.00050846,0.01982711,0.001819018,0.0008496704,0.0003051742,0.0003232951,0.07701275,0.04666177,0.004892883,0.3414603,0.5051991],"study_design_scores_gemma":[0.0004188758,0.0003380313,0.01509318,0.0002625737,0.0001511713,0.001026958,0.0002894382,0.7435091,0.08811305,0.01040141,0.1402178,0.0001784895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1177032,0.004331826,0.4329897,0.00103401,0.001044873,0.0009187969,0.1826109,0.2494607,0.00990595],"genre_scores_gemma":[0.1925483,0.000802276,0.5437609,0.0004646925,0.0001141661,0.0005379182,0.2504181,0.006766312,0.004587282],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01405891,"threshold_uncertainty_score":0.02795416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1215953248230728,"score_gpt":0.2362543337364523,"score_spread":0.1146590089133795,"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."}}