{"id":"W2787455114","doi":"10.48550/arxiv.1802.00036","title":"In Defense of Classical Image Processing: Fast Depth Completion on the CPU","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Python (programming language); Task (project management); Benchmark (surveying); Artificial neural network; Artificial intelligence; Code (set theory); Image (mathematics); Realization (probability); Source code; Computer engineering; Computer vision; Algorithm; 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":[0.001508937,0.001801275,0.001063544,0.0007566019,0.0007097519,0.002650057,0.003258083,0.001532097,0.0242078],"category_scores_gemma":[0.007428411,0.0007390924,0.0008909297,0.001472584,0.001026539,0.004527119,0.003711424,0.003600304,0.01415014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173869,"about_ca_system_score_gemma":0.002271356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005385122,"about_ca_topic_score_gemma":0.00669352,"domain_scores_codex":[0.9984608,0.0002324226,0.00009567366,0.0003643412,0.0006346332,0.0002121632],"domain_scores_gemma":[0.9977012,0.0004983008,0.0001002849,0.0009689432,0.0005486226,0.0001825974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001693001,0.0003125406,0.002409654,0.0005748967,0.0002198319,0.000365198,0.0002409156,0.0712468,0.02160583,0.03944525,0.2249192,0.6369669],"study_design_scores_gemma":[0.0001764435,0.0001685735,0.000857012,0.00007494335,0.00003867611,0.0002577813,0.00009298183,0.8716279,0.02764174,0.03935928,0.05965262,0.00005202509],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03252234,0.001782669,0.8602114,0.002442803,0.001078886,0.0002036241,0.001722047,0.07388495,0.02615125],"genre_scores_gemma":[0.3167695,0.0009957781,0.6391957,0.001509996,0.000404925,0.0004392213,0.007490777,0.006556086,0.02663798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0242078,"threshold_uncertainty_score":0.08098316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08535499141790359,"score_gpt":0.2302917553310851,"score_spread":0.1449367639131815,"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."}}