{"id":"W3097430696","doi":"10.1007/s00371-020-01998-z","title":"Joint restoration convolutional neural network for low-quality image super resolution","year":2020,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Compression artifact; Convolutional neural network; Artificial intelligence; Ringing artifacts; Residual; Benchmark (surveying); Concatenation (mathematics); Image (mathematics); Block (permutation group theory); Image restoration; Image quality; Feature (linguistics); Image compression; Pattern recognition (psychology); Interpolation (computer graphics); Computer vision; Image processing; 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":[],"consensus_categories":[],"category_scores_codex":[0.0006070746,0.0001695763,0.0001906343,0.00002836107,0.0003795561,0.0002516469,0.0006646758,0.00005583527,0.000004142205],"category_scores_gemma":[0.00009050762,0.0001323298,0.00009608498,0.000318061,0.0001339477,0.000898805,0.000454271,0.0002014908,0.00002455816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006254775,"about_ca_system_score_gemma":0.00006609855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006110832,"about_ca_topic_score_gemma":0.000001082715,"domain_scores_codex":[0.9983673,0.0002163132,0.0003620991,0.0004329786,0.0002858357,0.0003354713],"domain_scores_gemma":[0.9989946,0.0001737159,0.0001571695,0.0003271631,0.0002605663,0.00008674157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007825958,0.0004661648,0.0004178058,0.0004950939,0.0001169668,0.00002319058,0.004633592,0.03158392,0.130354,0.3370843,0.3971523,0.09689008],"study_design_scores_gemma":[0.0002642192,0.0002376188,0.00141035,0.00001996172,0.000004592678,0.00000556703,0.000003405322,0.9793056,0.001613287,0.01473094,0.002218246,0.0001861666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005426633,0.0001036636,0.9835176,0.009539622,0.0003188989,0.0003929159,0.000004819125,0.0006646213,0.0000311664],"genre_scores_gemma":[0.2149789,0.000002778199,0.7783251,0.00532137,0.001271234,0.00004573591,0.00002093923,0.00001665263,0.00001731102],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9477217,"threshold_uncertainty_score":0.5396255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06393398593342653,"score_gpt":0.3432241822792017,"score_spread":0.2792901963457752,"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."}}