{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000385988,0.00176335,0.0007228223,0.001059047,0.0002471268,0.0006466582,0.002144202,0.000996666,0.003273052],"category_scores_gemma":[0.001289014,0.0004714961,0.0005512967,0.001092863,0.0004261502,0.001893928,0.0011665,0.001064957,0.001467146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008560699,"about_ca_system_score_gemma":0.0009544707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01126179,"about_ca_topic_score_gemma":0.01972661,"domain_scores_codex":[0.9997241,0.00002540194,0.00001034408,0.0001045152,0.00009380195,0.00004184475],"domain_scores_gemma":[0.9997414,0.00004241859,0.00003651487,0.00005483304,0.0001067031,0.00001818275],"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":[0.0002182278,0.0001310713,0.003321383,0.0001197147,0.0001289049,0.0001352545,0.00004167461,0.3639329,0.01500974,0.006564097,0.01723891,0.593158],"study_design_scores_gemma":[0.000007964301,0.0000280387,0.0004743861,0.000006608276,0.00001142811,0.00004213871,0.000009266105,0.9905504,0.003706327,0.003119359,0.002034965,0.000009117369],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03471023,0.001027807,0.9456431,0.0003635716,0.0002507116,0.00008725199,0.001419362,0.01280831,0.003689559],"genre_scores_gemma":[0.5323365,0.0009481431,0.4478011,0.0005806516,0.0001888825,0.0001943497,0.006437813,0.0007210968,0.01079132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01126179,"threshold_uncertainty_score":0.02239245,"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."}}