{"id":"W2995824175","doi":"10.1016/j.neucom.2019.12.074","title":"Pairwise registration of TLS point clouds by deep multi-scale local features","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Department of Further Education, Employment, Science and Technology, Government of South Australia; National Natural Science Foundation of China","keywords":"Point cloud; Pairwise comparison; Computer science; Artificial intelligence; Outlier; Rotation (mathematics); Translation (biology); Pattern recognition (psychology); Scale (ratio); Robustness (evolution); Noise (video); Computer vision; Geography; Image (mathematics); Cartography","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":[0.0005200214,0.0011619,0.001073351,0.002172774,0.0006454397,0.001611772,0.001579811,0.001095004,0.003678621],"category_scores_gemma":[0.002590975,0.0008591273,0.001521985,0.004529248,0.0006552949,0.002078082,0.003635386,0.002027119,0.003895535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006087106,"about_ca_system_score_gemma":0.001966794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006956404,"about_ca_topic_score_gemma":0.01183294,"domain_scores_codex":[0.9989657,0.0001151117,0.00005174081,0.0002834561,0.0004210769,0.0001629241],"domain_scores_gemma":[0.9991521,0.00006655519,0.0001235455,0.0003511157,0.0002476604,0.00005916866],"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":[0.0005270409,0.0003264666,0.005082935,0.0002617034,0.000286849,0.0003026007,0.0003282836,0.2193892,0.07211931,0.007218395,0.01473026,0.6794271],"study_design_scores_gemma":[0.00002488414,0.00010768,0.00295525,0.00003201147,0.00003753802,0.0001768891,0.0001672786,0.9600326,0.0225355,0.007901575,0.005983483,0.00004540852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03112046,0.0002114299,0.9627044,0.0001507646,0.0001491984,0.00009287985,0.0005945645,0.003020479,0.001955822],"genre_scores_gemma":[0.6230598,0.0004086817,0.3660814,0.0001592043,0.00008864808,0.0002015726,0.00405052,0.0006789238,0.005271324],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006956404,"threshold_uncertainty_score":0.01383179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005357892170374875,"score_gpt":0.1949544817842768,"score_spread":0.1895965896139019,"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."}}