{"id":"W2898282475","doi":"10.1109/tip.2019.2929865","title":"Convolutional Deblurring for Natural Imaging","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Deblurring; Deconvolution; Image restoration; Computer science; Artificial intelligence; Computer vision; Blind deconvolution; Kernel (algebra); Point spread function; Image quality; Inpainting; Gaussian blur; Finite impulse response; Image processing; Image (mathematics); Algorithm; Mathematics","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003977293,0.0006773848,0.0005586924,0.0005813143,0.0007219965,0.001367097,0.001868141,0.000227427,0.000007819075],"category_scores_gemma":[0.0000421628,0.00073051,0.0003650431,0.0003913028,0.0002043086,0.002413779,0.00006245683,0.001592664,0.00002973495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004637961,"about_ca_system_score_gemma":0.0008656468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009453265,"about_ca_topic_score_gemma":0.00000198479,"domain_scores_codex":[0.9964036,0.00005896924,0.0006427777,0.0015579,0.0005674966,0.0007692723],"domain_scores_gemma":[0.9973343,0.0002150792,0.0004907246,0.001009222,0.0008240127,0.0001266397],"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":[0.0001242463,0.0004088694,0.00001456887,0.003504587,0.0001099843,0.0000297702,0.0009575058,0.01740741,0.04674831,0.000371199,0.0008223286,0.9295012],"study_design_scores_gemma":[0.0004877648,0.00003039045,0.000007493552,0.001197918,0.00005292018,0.00005921823,0.00002562267,0.9152722,0.06671148,0.01491994,0.000391689,0.0008433044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007282635,0.001719904,0.9916736,0.000888196,0.002245759,0.0009524612,0.00005039575,0.00207053,0.0003262557],"genre_scores_gemma":[0.3759645,0.00002284599,0.6227163,0.0003991595,0.0001076807,0.0003812251,0.00000996949,0.00007759898,0.0003207637],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9286579,"threshold_uncertainty_score":0.9996696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01685368270571917,"score_gpt":0.2999516227149906,"score_spread":0.2830979400092714,"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."}}