{"id":"W3164542873","doi":"10.1109/isbi48211.2021.9434058","title":"Real-Time Coarse-to-Fine Depth Estimation on Stereo Endoscopic Images With Self-Supervised Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Ground truth; Computer vision; Mean squared error; Matching (statistics); Pixel; Robotics; Stereo camera; Task (project management); Mean absolute error; Computer stereo vision; Robot; 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":[0.0001073611,0.0001564702,0.0001721014,0.0001011408,0.0001510883,0.0002247988,0.0002820971,0.0000224947,0.0001355048],"category_scores_gemma":[0.00006615527,0.0001257059,0.00002853063,0.0004699983,0.00001323394,0.0005717921,0.000174462,0.0001418718,0.0004512855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004414066,"about_ca_system_score_gemma":0.00007756482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001118481,"about_ca_topic_score_gemma":0.000005243685,"domain_scores_codex":[0.9987338,0.00008349607,0.0001692362,0.0004590059,0.000289202,0.0002653257],"domain_scores_gemma":[0.9991403,0.0001156579,0.00005081904,0.000437822,0.0001241572,0.0001312316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003601183,0.0002720702,0.002098118,0.00005079416,0.00004216576,0.0002492345,0.00155686,0.02164074,0.08468893,0.006265818,0.001528858,0.8815704],"study_design_scores_gemma":[0.0008100883,0.0002942159,0.002233348,0.0001097089,0.00000643041,0.00002525684,0.00006763826,0.9406788,0.05446446,0.0001645733,0.0009193294,0.0002261766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02583303,0.00001183318,0.9427776,0.001386977,0.00007632662,0.0001439816,4.392566e-7,0.0006878564,0.02908195],"genre_scores_gemma":[0.1330162,0.00001012996,0.8620637,0.000605144,0.00002108199,0.000008521741,0.000006359874,0.00001592814,0.004252905],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.919038,"threshold_uncertainty_score":0.5800513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01076635906537876,"score_gpt":0.2654847815192709,"score_spread":0.2547184224538921,"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."}}