{"id":"W3177293728","doi":"10.1109/tip.2021.3092814","title":"Structure-Aware Motion Deblurring Using Multi-Adversarial Optimized CycleGAN","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Hong Kong Polytechnic University; Ministry of Science and Technology, Taiwan; National Natural Science Foundation of China","keywords":"Deblurring; Computer science; Artificial intelligence; Kernel (algebra); Image restoration; Pattern recognition (psychology); Image (mathematics); Adversarial system; Computer vision; Convolutional neural network; Image processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005320167,0.001072219,0.0006400162,0.0004171026,0.0002567982,0.0004621696,0.0007775023,0.0006905975,0.001327857],"category_scores_gemma":[0.001302308,0.0003999447,0.0007061021,0.0002812602,0.0006768852,0.0008745793,0.001035634,0.001202348,0.0003858623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005511399,"about_ca_system_score_gemma":0.0005100275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002015101,"about_ca_topic_score_gemma":0.002992209,"domain_scores_codex":[0.9997086,0.00005784831,0.00001449659,0.00008803896,0.00009558663,0.00003534082],"domain_scores_gemma":[0.9996319,0.000143783,0.000057413,0.0000845372,0.00006183287,0.00002048332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002163968,0.0000564282,0.0007495206,0.0001636951,0.0001187579,0.00019453,0.0001434264,0.7189785,0.07374366,0.01168701,0.002767449,0.1911807],"study_design_scores_gemma":[0.000007503096,0.00003814066,0.0001448335,0.00001033507,0.00001543298,0.00008273806,0.00000787514,0.9834389,0.01205113,0.002721834,0.001468337,0.00001292745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01649348,0.0004678041,0.9805147,0.0001347111,0.0000390867,0.00003509661,0.0000467087,0.0006057276,0.001662668],"genre_scores_gemma":[0.5413197,0.0008667691,0.4478111,0.0004919187,0.00005628007,0.0001438089,0.0004098433,0.0003481983,0.008552375],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002015101,"threshold_uncertainty_score":0.004442096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02502573497487601,"score_gpt":0.2987943317873849,"score_spread":0.2737685968125089,"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."}}