{"id":"W4379928090","doi":"10.1109/tpami.2023.3283979","title":"Blind Image Deconvolution Using Variational Deep Image Prior","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Prior probability; Artificial intelligence; Deconvolution; Computer science; Maximum a posteriori estimation; Image (mathematics); Blind deconvolution; Image restoration; Generalization; Pattern recognition (psychology); Benchmark (surveying); Computer vision; Pixel; Mathematics; Image processing; Algorithm; Maximum likelihood; Statistics; Bayesian probability","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003482396,0.0002233566,0.0002609021,0.0009421707,0.0003890169,0.0002813621,0.0004751217,0.0000670026,0.00008719245],"category_scores_gemma":[0.00001592655,0.0002170038,0.0001828106,0.002394029,0.00009840947,0.0009363048,0.00001536123,0.0002510118,0.00006401817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007253186,"about_ca_system_score_gemma":0.00003955651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002447328,"about_ca_topic_score_gemma":0.0001843384,"domain_scores_codex":[0.9983085,0.0000742821,0.0003936532,0.0006138327,0.0003155155,0.000294155],"domain_scores_gemma":[0.9989683,0.0001392134,0.0001502736,0.0004633896,0.0001728074,0.0001060204],"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":[0.00002083906,0.0001761688,0.0002156754,0.0000385593,0.0003611141,0.00003123071,0.0005185938,0.021072,0.02457364,0.0001773676,0.00001089726,0.9528039],"study_design_scores_gemma":[0.00008176773,0.00003541425,0.0005375494,0.00001626863,0.0001743955,0.00001384797,0.00001757358,0.9025198,0.09371341,0.002657973,0.0000117061,0.0002202944],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00148346,0.00004822024,0.9973695,0.0003261325,0.0001236883,0.0001288184,0.000023071,0.0004659508,0.00003111955],"genre_scores_gemma":[0.6959627,0.0001393464,0.3036125,0.0001565561,0.00001809478,0.00002179299,0.000007560901,0.00001392055,0.00006761005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9525836,"threshold_uncertainty_score":0.8849161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02791397047570955,"score_gpt":0.3174776599293144,"score_spread":0.2895636894536049,"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."}}