{"id":"W2896184058","doi":"10.1109/tip.2018.2874284","title":"High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; National Natural Science Foundation of China","keywords":"Image restoration; Regularization (linguistics); Artificial intelligence; Iterative reconstruction; Pixel; Computer science; Residual; Image resolution; Pattern recognition (psychology); Deblurring; Norm (philosophy); Mathematics; Computer vision; Algorithm; Image (mathematics); Image processing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003199402,0.000321905,0.0002779233,0.0001586041,0.001118977,0.0008703976,0.0004678364,0.0001703031,0.000009944023],"category_scores_gemma":[0.00004122563,0.0003361622,0.00004977324,0.001009564,0.000452623,0.004644226,0.00001714188,0.0003084462,0.00000555663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002808664,"about_ca_system_score_gemma":0.0002104139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009495468,"about_ca_topic_score_gemma":0.00004411587,"domain_scores_codex":[0.9977679,0.0001441949,0.0004382115,0.000811659,0.0004518217,0.0003862679],"domain_scores_gemma":[0.9982681,0.0000322307,0.0003208552,0.0005610851,0.0006940278,0.000123745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001072758,0.0001664878,0.00007610284,0.0003114922,0.00001870143,0.00001339527,0.0007124997,0.0002333674,0.7773991,0.0005712933,0.00003472244,0.2203555],"study_design_scores_gemma":[0.0006652742,0.0001229846,0.0005547369,0.0003185425,0.00004894891,0.00008845125,0.00004852613,0.3511722,0.6008618,0.04544,0.00002063613,0.0006578906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05340414,0.00005665577,0.9448673,0.0002953565,0.0002626663,0.0002356309,0.00003135037,0.0007849039,0.00006201288],"genre_scores_gemma":[0.5016505,0.000004859629,0.4981211,0.0001230933,0.00006240298,0.000004910206,0.000002485323,0.00001498182,0.00001569768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4482463,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01857909878811228,"score_gpt":0.3071245329623622,"score_spread":0.2885454341742499,"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."}}