{"id":"W2963416674","doi":"10.1109/crv.2018.00013","title":"In Defense of Classical Image Processing: Fast Depth Completion on the CPU","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":321,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Python (programming language); Artificial neural network; Benchmark (surveying); Task (project management); Artificial intelligence; Code (set theory); Image processing; Image (mathematics); Source code; Computer engineering; Computer vision; Operating system; Programming language","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":[0.001339809,0.00170517,0.000999177,0.0006928236,0.0006627442,0.002348059,0.00311277,0.001305134,0.02308178],"category_scores_gemma":[0.006316001,0.0006998242,0.000820378,0.001342781,0.0009138959,0.003945326,0.003320942,0.003194023,0.01217918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102198,"about_ca_system_score_gemma":0.002234882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005568063,"about_ca_topic_score_gemma":0.007007338,"domain_scores_codex":[0.9986473,0.0001934263,0.00008418142,0.0003080541,0.0005724712,0.0001946354],"domain_scores_gemma":[0.9980533,0.0004398609,0.00008921884,0.0007668773,0.0004893605,0.0001613607],"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":[0.0017017,0.0003075783,0.002448155,0.0005596883,0.0002209772,0.0003748152,0.0002428872,0.07297329,0.02549013,0.0352783,0.1939756,0.6664268],"study_design_scores_gemma":[0.0001701534,0.0001774365,0.0009079244,0.00006862107,0.00003969392,0.0002529353,0.00009107528,0.8839704,0.03056149,0.03057612,0.05313261,0.00005152781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03427752,0.00151352,0.8695498,0.001939161,0.0008695209,0.0001945051,0.001465953,0.06649762,0.02369247],"genre_scores_gemma":[0.3221709,0.000888997,0.6385586,0.001257568,0.000325319,0.0004271719,0.006524244,0.005561787,0.0242853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02308178,"threshold_uncertainty_score":0.07721627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03142796426267123,"score_gpt":0.3109826089730189,"score_spread":0.2795546447103476,"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."}}