{"id":"W3199549300","doi":"10.1109/tpami.2021.3115139","title":"Learning Frequency Domain Priors for Image Demoireing","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"National Key Research and Development Program of China; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Discrete cosine transform; Frequency domain; Block (permutation group theory); Convolution (computer science); Convolutional neural network; Computer vision; Margin (machine learning); Pattern recognition (psychology); Image restoration; Image (mathematics); Prior probability; Image processing; Mathematics; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001181284,0.000969268,0.001026756,0.0008640687,0.0002676073,0.0006269562,0.001276626,0.001460207,0.001259853],"category_scores_gemma":[0.002486072,0.0004101912,0.0007601713,0.0005225231,0.0007716105,0.001532889,0.001049008,0.001858689,0.0005920234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000780057,"about_ca_system_score_gemma":0.0007259265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003039109,"about_ca_topic_score_gemma":0.004314161,"domain_scores_codex":[0.9995969,0.00006700537,0.00001821309,0.0001468131,0.0001187512,0.00005224145],"domain_scores_gemma":[0.9992303,0.0002436881,0.00009333686,0.0002297814,0.0001583686,0.00004445793],"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":[0.0003583183,0.0001647435,0.001440631,0.0002008316,0.0001031479,0.0001657377,0.0000850377,0.4207419,0.04402281,0.006648838,0.007335695,0.5187322],"study_design_scores_gemma":[0.000009556537,0.00003978607,0.0005061112,0.00001198616,0.00001438228,0.00008935081,0.0000130663,0.9841601,0.009582397,0.003916649,0.001646609,0.000009957375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04332144,0.0009163399,0.9515638,0.0003775336,0.00006416595,0.00005932185,0.0002044691,0.001933753,0.001559105],"genre_scores_gemma":[0.5786673,0.001228722,0.4064502,0.0008029802,0.0001593083,0.0001140206,0.001770547,0.0004916683,0.01031525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003039109,"threshold_uncertainty_score":0.006247342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01345762125044942,"score_gpt":0.2742594237464342,"score_spread":0.2608018024959848,"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."}}