{"id":"W3186685722","doi":"10.1109/tci.2021.3098927","title":"Online Training of Stereo Self-Calibration Using Monocular Depth Estimation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Imaging","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"European Research Council","keywords":"Artificial intelligence; Monocular; Computer science; Computer vision; Benchmark (surveying); Calibration; Context (archaeology); Stereo cameras; Feature (linguistics); Camera resectioning; Measured depth; Outlier; Consistency (knowledge bases); Stereopsis; Mathematics; Engineering; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.000123871,0.0001604567,0.0001900875,0.0002449187,0.000230791,0.0001309119,0.0002028566,0.00002765998,0.00001654971],"category_scores_gemma":[0.00001117582,0.0001844096,0.0001101942,0.0006189723,0.00003480564,0.001380466,0.000005978868,0.000178021,0.000004220749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008341327,"about_ca_system_score_gemma":0.0002458841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006241187,"about_ca_topic_score_gemma":0.000002328703,"domain_scores_codex":[0.9985112,0.00009701138,0.0004182862,0.0003813721,0.0003943504,0.0001977886],"domain_scores_gemma":[0.9990523,0.0001894472,0.0001573758,0.0002452896,0.0002775089,0.00007805023],"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":[0.00000283847,0.0001742217,0.00001990122,0.00001372584,0.00002032471,0.00001151136,0.000550501,0.7688991,0.002414427,0.0004960027,0.000003790818,0.2273937],"study_design_scores_gemma":[0.0004484427,0.00001501043,0.0002577702,0.00009073794,0.00001894097,0.0001037399,0.000171928,0.981259,0.01384522,0.003591439,0.00002729274,0.0001705037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009233678,0.00005774243,0.9894036,0.0005433568,0.0003735553,0.00009569545,0.00001086919,0.0002045059,0.00007701451],"genre_scores_gemma":[0.4971719,0.000002943647,0.5025176,0.0002623242,0.00001406184,0.000002046671,0.00001033661,0.000009882713,0.00000884538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4879382,"threshold_uncertainty_score":0.7520006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04194501124762357,"score_gpt":0.3170729384896085,"score_spread":0.2751279272419849,"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."}}