{"id":"W4389751994","doi":"10.20944/preprints202312.1045.v1","title":"Improving 3D Building Segmentation on 3D City Models Through Simulated Data and Contextual Analysis for Building Extraction","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Mitacs; Université de Sherbrooke","keywords":"Segmentation; Computer science; Context (archaeology); Field (mathematics); Markov random field; Architecture; Polygon mesh; Data mining; Ranging; Resource (disambiguation); Artificial intelligence; Image segmentation; Machine learning; Geography; Computer graphics (images)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.0004226161,0.0008170319,0.0006201279,0.00189561,0.0004293787,0.001197736,0.001000801,0.0007683508,0.001895009],"category_scores_gemma":[0.001805721,0.0006328343,0.001062794,0.002127327,0.0005367494,0.0007003693,0.0008541795,0.0005461492,0.0008214927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057155,"about_ca_system_score_gemma":0.001373422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04613334,"about_ca_topic_score_gemma":0.1263852,"domain_scores_codex":[0.9996397,0.00007057114,0.00001846085,0.00008616396,0.0001349762,0.00005006959],"domain_scores_gemma":[0.9994478,0.0002148564,0.00004125857,0.0001318856,0.0001401022,0.0000241668],"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":[0.0001023792,0.00008455558,0.005221479,0.0001286199,0.00008228416,0.0001167421,0.0001372527,0.8977595,0.01173834,0.002108711,0.001232164,0.08128791],"study_design_scores_gemma":[0.000003731089,0.000007436245,0.001011537,0.00000757731,0.000006534548,0.00001811158,0.00002903682,0.9945092,0.002932164,0.0005924125,0.0008754162,0.000007010392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1728187,0.0001811272,0.8166519,0.0001429728,0.000040805,0.0001385462,0.002214854,0.005086869,0.002724335],"genre_scores_gemma":[0.5762483,0.0002411368,0.4158636,0.00005097219,0.00001843476,0.000129393,0.005804209,0.0005415956,0.001102435],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04613334,"threshold_uncertainty_score":0.09172964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2280732709833718,"score_gpt":0.4002380470819673,"score_spread":0.1721647760985955,"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."}}