{"id":"W2905260191","doi":"10.1109/cvpr.2019.00458","title":"PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":242,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Ground truth; Segmentation; Piecewise; Benchmark (surveying); RGB color model; Plane (geometry); Ground plane; Consistency (knowledge bases); Image segmentation; Augmented reality; Image plane; Robotics; Deep learning; Pattern recognition (psychology); Image (mathematics); Robot; Mathematics; Geography; 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":[0.0003110595,0.001003063,0.0005906487,0.0007223854,0.000210624,0.000899755,0.001760737,0.0009139912,0.00368378],"category_scores_gemma":[0.001075066,0.0005704742,0.0007103237,0.0006814393,0.0004160141,0.001270875,0.0009826162,0.0008363453,0.001739278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006186046,"about_ca_system_score_gemma":0.0007187212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007956073,"about_ca_topic_score_gemma":0.01308847,"domain_scores_codex":[0.9997082,0.00001924317,0.0000106618,0.00009734302,0.000125145,0.00003945761],"domain_scores_gemma":[0.9997211,0.0000401348,0.00003828718,0.0001075979,0.00007717807,0.00001564607],"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":[0.0002508948,0.00007048995,0.001753903,0.0001674803,0.000151731,0.0001666504,0.00006704986,0.1883207,0.05095459,0.006612582,0.01079427,0.7406896],"study_design_scores_gemma":[0.000007927348,0.00006690107,0.0008546408,0.0000210481,0.00003064292,0.0002089079,0.00001765838,0.9643868,0.02589611,0.002458161,0.006029245,0.0000219189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02354686,0.0004678662,0.964868,0.0001176794,0.00008757433,0.00006635823,0.0005836816,0.006285444,0.003976367],"genre_scores_gemma":[0.2681106,0.0006878418,0.7171621,0.0002636012,0.00005568095,0.00008570781,0.003298223,0.0007159627,0.009620274],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007956073,"threshold_uncertainty_score":0.01581955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00936048908813515,"score_gpt":0.2067988968933366,"score_spread":0.1974384078052015,"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."}}