{"id":"W2798927139","doi":"10.1109/cvpr.2018.00037","title":"GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":401,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Normal; Surface (topology); Consistency (knowledge bases); Computer science; Artificial intelligence; Residual; Depth map; Artificial neural network; Kernel (algebra); Joint (building); Computer vision; Mathematics; Pattern recognition (psychology); Algorithm; Image (mathematics); Geometry","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":[0.0001733524,0.00007432561,0.00008356785,0.00005990486,0.0001731861,0.000117889,0.000154039,0.0000179264,0.00001284197],"category_scores_gemma":[0.00004836099,0.00006171131,0.00002104281,0.0004296299,0.00003548594,0.0006363458,0.0001371078,0.00003989807,0.00002047404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009862572,"about_ca_system_score_gemma":0.00001007113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000137157,"about_ca_topic_score_gemma":0.000007731367,"domain_scores_codex":[0.9993119,0.00001152832,0.0001266388,0.0002135726,0.00009788702,0.0002385273],"domain_scores_gemma":[0.999567,0.00006809484,0.00004557081,0.0001771215,0.00007320644,0.00006894769],"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":[0.000006907693,0.00001343707,0.002264984,0.000008287573,0.000003907698,8.0897e-7,0.00008722836,0.0112824,0.0001933898,0.005052251,0.005389244,0.9756972],"study_design_scores_gemma":[0.0002187387,0.000103809,0.01295391,0.000004553562,0.00000148275,0.000009838282,0.000004429551,0.9825481,0.0007589762,0.001509659,0.001796459,0.00009007716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02101735,0.0001004198,0.9768613,0.0005028855,0.0002810973,0.0001249443,3.544311e-7,0.000108983,0.001002649],"genre_scores_gemma":[0.4409861,0.000003531689,0.5582281,0.0004839069,0.00006437302,0.000001518029,8.883547e-7,0.000003356116,0.0002281958],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9756071,"threshold_uncertainty_score":0.2516514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02687501381210139,"score_gpt":0.2854791085497823,"score_spread":0.2586040947376809,"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."}}