{"id":"W4221142437","doi":"10.48550/arxiv.2202.00179","title":"Blind Image Deconvolution Using Variational Deep Image Prior","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Prior probability; Deconvolution; Artificial intelligence; Image (mathematics); Computer science; Blind deconvolution; Generalization; Maximum a posteriori estimation; Benchmark (surveying); Constraint (computer-aided design); Pattern recognition (psychology); Image restoration; Network architecture; A priori and a posteriori; Algorithm; Computer vision; Mathematics; Image processing; Maximum likelihood; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009013484,0.001116317,0.000825103,0.0006860658,0.0003040493,0.0009976855,0.001219027,0.001322172,0.002218123],"category_scores_gemma":[0.002118581,0.0006824632,0.001092436,0.0005692355,0.001383561,0.00171228,0.00190347,0.002397584,0.0007706922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000998538,"about_ca_system_score_gemma":0.001453385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003547501,"about_ca_topic_score_gemma":0.003777401,"domain_scores_codex":[0.9995728,0.0001017076,0.00002113226,0.0001165863,0.0001471996,0.00004064565],"domain_scores_gemma":[0.9994854,0.000207081,0.00006093972,0.0001083257,0.00009879934,0.00003948879],"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":[0.0001690325,0.00005524634,0.0005105021,0.0002272777,0.0001111036,0.0001473493,0.00009898404,0.7356805,0.03296897,0.06528848,0.003921715,0.1608209],"study_design_scores_gemma":[0.000007597843,0.00001391908,0.00005693499,0.000009885085,0.0000069291,0.00004384065,0.000004721056,0.9800518,0.004783054,0.01359673,0.001412836,0.00001171074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001530658,0.0001053015,0.997443,0.00006096565,0.0000101371,0.00001018157,0.00003319234,0.0002274129,0.0005791137],"genre_scores_gemma":[0.2163602,0.0009284096,0.7749734,0.0002923001,0.00008893538,0.0001554154,0.0004862188,0.0004638948,0.006251225],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003547501,"threshold_uncertainty_score":0.007420361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05173827587366066,"score_gpt":0.2111147455082858,"score_spread":0.1593764696346252,"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."}}