{"id":"W3124885591","doi":"10.48550/arxiv.2101.09951","title":"Fast & Robust Image Interpolation using Gradient Graph Laplacian Regularizer","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Piecewise; Mathematics; Algorithm; Laplacian matrix; Pixel; Quadratic equation; Interpolation (computer graphics); Conjugate gradient method; Graph; Planar; Computer science; Artificial intelligence; Image (mathematics); Combinatorics; Geometry; Mathematical analysis","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":[0.0007160942,0.0009458804,0.0007970379,0.0007306102,0.0003377027,0.0007100367,0.001148767,0.0009246314,0.002894322],"category_scores_gemma":[0.002052356,0.0004037711,0.0006740052,0.0008451456,0.0006973775,0.00118612,0.001131317,0.001388595,0.001228929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005528975,"about_ca_system_score_gemma":0.0009525316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003971555,"about_ca_topic_score_gemma":0.004480121,"domain_scores_codex":[0.9995936,0.00008461533,0.0000157801,0.0001013466,0.0001666352,0.00003816321],"domain_scores_gemma":[0.9995393,0.0001448491,0.00005807518,0.0001098028,0.000119959,0.00002814317],"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":[0.0002636083,0.0001060975,0.0004464857,0.0001576524,0.00006716874,0.0001731225,0.0001247026,0.5878347,0.03039953,0.0257695,0.009047676,0.3456098],"study_design_scores_gemma":[0.000005194841,0.00001821749,0.00004103499,0.000003315927,0.000003115524,0.00002882415,0.000004792366,0.9929661,0.002912464,0.003157317,0.0008538084,0.000005752501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008316968,0.000162297,0.9882963,0.0001482002,0.00003368806,0.00002545829,0.00006677746,0.001346719,0.001603608],"genre_scores_gemma":[0.2611442,0.0002844372,0.730604,0.0001845318,0.00004882789,0.00008592148,0.0004609839,0.0004804029,0.0067067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003971555,"threshold_uncertainty_score":0.009682417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07831453599808524,"score_gpt":0.1994874090030349,"score_spread":0.1211728730049497,"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."}}