{"id":"W4410516601","doi":"10.3390/jimaging11050167","title":"Comparing Geodesic Filtering to State-of-the-Art Algorithms: A Comprehensive Study and CUDA Implementation","year":2025,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Geodesic; Computer science; Algorithm; CUDA; Speedup; Noise (video); Image processing; Computation; Median filter; Collaborative filtering; Noise reduction; Filter (signal processing); Artificial intelligence; Computer vision; Image (mathematics); Recommender system; Machine learning; Mathematics; Parallel computing","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":[],"consensus_categories":[],"category_scores_codex":[0.0005749593,0.00008867577,0.0002274024,0.0002357839,0.0001164026,0.0001883669,0.0004162904,0.000005274806,0.000001565878],"category_scores_gemma":[0.00003444283,0.00006987998,0.00005504955,0.0003614777,0.00002214413,0.0004494086,0.0003471569,0.0001394544,6.372121e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004642112,"about_ca_system_score_gemma":0.00006827917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003961679,"about_ca_topic_score_gemma":0.000006052866,"domain_scores_codex":[0.9988636,0.0001824801,0.0004345837,0.0001282535,0.0002398614,0.0001512005],"domain_scores_gemma":[0.9991521,0.0001319028,0.0002393611,0.0001773571,0.0002532747,0.0000459971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005342251,0.0001207221,0.07222231,0.00006917268,0.0001463513,0.00009517417,0.009188069,0.002015758,0.09001868,0.000103056,0.001673067,0.8242942],"study_design_scores_gemma":[0.00650937,0.0005192828,0.7322445,0.001058748,0.0001697182,0.0004172037,0.005511592,0.1250366,0.1194212,0.00526176,0.003341599,0.0005084359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3850852,0.0001481102,0.6138449,0.0004391151,0.0003065779,0.0001090923,2.593863e-7,0.000005855025,0.00006094075],"genre_scores_gemma":[0.8807107,0.000004279315,0.118822,0.0003942944,0.00002291844,0.000001361523,5.880453e-8,0.000004142458,0.00004027199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8237858,"threshold_uncertainty_score":0.2849623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02767354514219185,"score_gpt":0.3477715608758781,"score_spread":0.3200980157336863,"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."}}