{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003127046,0.0002572404,0.0003865776,0.0003416741,0.0004659029,0.00005293197,0.0002090391,0.00004143872,0.0007995694],"category_scores_gemma":[0.000001563517,0.0002517547,0.0004683647,0.0008666212,0.00002445672,0.00005821291,0.000005552845,0.0003603897,0.000007501277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006737968,"about_ca_system_score_gemma":0.000007986238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006497151,"about_ca_topic_score_gemma":0.001379521,"domain_scores_codex":[0.9984917,0.00005210979,0.0004721938,0.0003745389,0.0002562097,0.0003532651],"domain_scores_gemma":[0.9993771,0.00008172943,0.00005910645,0.0003302308,0.00004027021,0.0001116079],"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":[0.00002090484,0.00005241514,0.0001624337,0.00001785982,0.0007077761,0.00000307454,0.0001065563,0.8267961,0.00009183263,0.000005139841,0.0001220793,0.1719138],"study_design_scores_gemma":[0.0001187225,0.00014436,0.00007896217,0.000006360267,0.001109529,0.000005760186,0.00008240408,0.9939966,0.003487127,0.00005937833,0.0006253878,0.0002854003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01869536,0.0003455226,0.9797416,0.0003071367,0.0003130043,0.0001200798,0.0002555984,0.0001445092,0.00007713564],"genre_scores_gemma":[0.998022,0.000238564,0.000651666,0.0004019443,0.00007733313,0.0001538542,0.00006741131,0.00003517025,0.0003520559],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9793267,"threshold_uncertainty_score":0.9999934,"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."}}