{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003332274,0.0002026525,0.0002847729,0.0003451544,0.0003273774,0.0002374837,0.0003657093,0.00005652097,0.0001080082],"category_scores_gemma":[0.00001402948,0.0001978536,0.0002763852,0.0009731742,0.00005097923,0.0003789332,0.000008652343,0.0002713602,0.00001232916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004682445,"about_ca_system_score_gemma":0.00003338099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001954729,"about_ca_topic_score_gemma":0.0003877562,"domain_scores_codex":[0.9984348,0.0001076632,0.0003556113,0.0005998791,0.0002215595,0.0002804881],"domain_scores_gemma":[0.9990527,0.0001636799,0.0001039475,0.0004420109,0.000151418,0.00008621725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004826734,0.0001434957,0.0003726532,0.00003819874,0.0004284031,0.00004916188,0.000830592,0.001600915,0.03050443,0.0006091247,0.000009122492,0.9654091],"study_design_scores_gemma":[0.00009151698,0.0001488321,0.000145239,0.00003475422,0.0002382103,0.00001848591,0.0001198113,0.08426423,0.9114797,0.00303747,0.0001058584,0.0003159633],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003628453,0.0001003083,0.9950662,0.0005191215,0.0001174799,0.000149538,0.00001081026,0.0002120647,0.0001960507],"genre_scores_gemma":[0.8326542,0.0002123897,0.1664787,0.0002865008,0.00001450121,0.00005468801,0.000005703553,0.0000122983,0.0002809399],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9650931,"threshold_uncertainty_score":0.8068235,"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."}}