{"id":"W4210368713","doi":"10.1109/tpami.2022.3145877","title":"Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Point cloud; Computer science; Artificial intelligence; Net (polyhedron); Prior probability; Normal; Feature (linguistics); Property (philosophy); Pattern recognition (psychology); Artificial neural network; Point (geometry); Surface (topology); Algorithm; Computer vision; 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":[0.0009952409,0.001347371,0.0009624917,0.0009010646,0.000385466,0.0007390206,0.002510207,0.001360839,0.002124504],"category_scores_gemma":[0.002952359,0.0007133394,0.0007703045,0.0008493367,0.0006879607,0.001507542,0.001495537,0.001408878,0.0009973552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027426,"about_ca_system_score_gemma":0.000877794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01141712,"about_ca_topic_score_gemma":0.01266728,"domain_scores_codex":[0.999644,0.00004383059,0.00001638908,0.0001144518,0.0001302918,0.00005100785],"domain_scores_gemma":[0.9993302,0.0002038592,0.00006881551,0.0001287102,0.0002341014,0.00003433356],"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":[0.0002493023,0.00007094755,0.001908371,0.00007994707,0.00006887387,0.0001054872,0.0000632127,0.6343653,0.00826367,0.004522503,0.006514694,0.3437877],"study_design_scores_gemma":[0.00000440118,0.00001389329,0.0001048495,0.000003289235,0.000003949722,0.00001181,0.000002914685,0.9970648,0.001268651,0.001157583,0.0003601552,0.000003717061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01775924,0.0002662332,0.976218,0.0001217255,0.0000680642,0.0000541663,0.0002065315,0.004188746,0.001117243],"genre_scores_gemma":[0.4739068,0.0004964144,0.5155495,0.0003284796,0.0001035345,0.0002460832,0.002082607,0.0005576255,0.006728898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01141712,"threshold_uncertainty_score":0.02270132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01734719637563666,"score_gpt":0.2423185849393213,"score_spread":0.2249713885636846,"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."}}