{"id":"W4381615821","doi":"10.1061/jcemd4.coeng-13020","title":"Integrating Inverse Photogrammetry and a Deep Learning–Based Point Cloud Segmentation Approach for Automated Generation of BIM Models","year":2023,"lang":"en","type":"article","venue":"Journal of Construction Engineering and Management","topic":"3D Surveying and Cultural Heritage","field":"Earth and Planetary Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Point cloud; Photogrammetry; Computer science; Segmentation; Artificial intelligence; Point (geometry); Deep learning; Computer vision; Testbed; Data mining; 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":[0.0003929391,0.00006461865,0.0001059981,0.0001636418,0.00006003771,0.00003422483,0.00002432319,0.00002541303,0.00000420198],"category_scores_gemma":[0.00001826372,0.00005256979,0.00003063923,0.0001681142,0.00001800167,0.0001384717,0.000003629811,0.00006058749,1.632464e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000453973,"about_ca_system_score_gemma":0.000004396843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002945154,"about_ca_topic_score_gemma":0.00001120548,"domain_scores_codex":[0.9995155,0.00002527268,0.0002068443,0.00007198746,0.0001002045,0.00008017039],"domain_scores_gemma":[0.9997349,0.00002927181,0.0001237595,0.00002494157,0.00004727772,0.00003986577],"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":[0.00002029823,0.000004473531,0.002154283,0.0002032217,0.00004816268,0.000001775256,0.0001916472,0.9282763,0.0007439028,0.0001182393,0.00004689024,0.06819082],"study_design_scores_gemma":[0.0003959353,0.00009414477,0.002713599,0.00003212886,0.00002789883,0.00002080444,0.00180512,0.9945637,0.0001944536,0.00003273796,0.00006324267,0.00005622494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5822279,0.0001221453,0.4171641,0.00001647248,0.0002235113,0.0001223552,0.000003707384,0.00006144518,0.00005830724],"genre_scores_gemma":[0.9028604,0.0001886471,0.0968474,0.000007679595,0.00004095691,0.00000158908,0.00003937449,0.000002544135,0.00001138796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3206325,"threshold_uncertainty_score":0.2143734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02207147401977677,"score_gpt":0.2108570291887684,"score_spread":0.1887855551689916,"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."}}