{"id":"W3174969937","doi":"10.1109/cvpr46437.2021.01573","title":"Mirror3D: Depth Refinement for Mirror Surfaces","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Compute Canada","keywords":"Computer science; Context (archaeology); Artificial intelligence; Depth map; RGB color model; Plane (geometry); Key (lock); Computer vision; Surface (topology); Plane mirror; Depth perception; Optics; Mathematics; Geometry; Geology; Physics; Image (mathematics)","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":[0.00009114303,0.00007241614,0.00008835681,0.00002484661,0.00008695818,0.0000899822,0.0002726131,0.00001450348,0.0001024268],"category_scores_gemma":[0.00004427219,0.00006063933,0.0000501953,0.0001650943,0.00001013562,0.0002655246,0.0001587257,0.0000340064,0.00005437173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001462899,"about_ca_system_score_gemma":0.00004728916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001044543,"about_ca_topic_score_gemma":0.00006903876,"domain_scores_codex":[0.9992565,0.00001396233,0.0001276992,0.000284412,0.0001248795,0.000192558],"domain_scores_gemma":[0.9994062,0.00006033055,0.00002848082,0.0003355165,0.000108624,0.00006083475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001057791,0.0002428298,0.001079791,0.00005524586,0.00003242669,0.00004462887,0.0004753687,0.00003732361,0.08109503,0.2001321,0.02767207,0.6891227],"study_design_scores_gemma":[0.000826254,0.00006148453,0.003136631,0.00002397826,0.000004085753,0.00001699793,0.0001891841,0.1390094,0.1371425,0.007552255,0.7117484,0.0002888087],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001775815,0.000204876,0.9795955,0.006289277,0.0003050094,0.00008793901,0.000001101429,0.0001431993,0.01159722],"genre_scores_gemma":[0.03898887,0.00001639134,0.9484336,0.002332943,0.000008206921,0.000012415,0.000003068699,0.000005419616,0.01019911],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6888338,"threshold_uncertainty_score":0.24728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04131132006777828,"score_gpt":0.3270345847215561,"score_spread":0.2857232646537778,"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."}}