{"id":"W2567338558","doi":"10.1109/crv.2016.29","title":"Image Restoration via Deep-Structured Stochastically Fully-Connected Conditional Random Fields (DSFCRFs) for Very Low-Light Conditions","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conditional random field; Image restoration; Artificial intelligence; Computer science; Noise (video); Image (mathematics); Computer vision; Random field; Set (abstract data type); Image processing; Pattern recognition (psychology); Mathematics; Statistics","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":[0.0007557466,0.0007240053,0.0005651833,0.0004567968,0.0002401116,0.0004697771,0.001106375,0.0009639623,0.001223117],"category_scores_gemma":[0.002139149,0.0003075703,0.0008215546,0.0003200221,0.0007330337,0.0009035299,0.0006640501,0.001311033,0.0002796985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007448774,"about_ca_system_score_gemma":0.0009350735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007206666,"about_ca_topic_score_gemma":0.008331109,"domain_scores_codex":[0.999787,0.0000559652,0.000008458285,0.00005131949,0.00007009849,0.0000271103],"domain_scores_gemma":[0.9994186,0.0002781425,0.00008396362,0.00007648233,0.00011177,0.00003100669],"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":[0.00009805377,0.0000512167,0.0003699833,0.00008980663,0.00004823475,0.0001011986,0.0000505677,0.9037067,0.01547342,0.007060582,0.001654144,0.07129612],"study_design_scores_gemma":[0.000002318096,0.0000102474,0.00008951718,0.000003630529,0.000004204961,0.00001717711,0.000002036202,0.995643,0.001965344,0.002054323,0.0002023663,0.000005877848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01807943,0.000182075,0.979742,0.0002185855,0.00003175933,0.00002764348,0.00009494725,0.0007816335,0.0008418746],"genre_scores_gemma":[0.7306761,0.0003447816,0.2645596,0.0003125195,0.00005140603,0.00009229159,0.0004692473,0.0001998005,0.003294372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007206666,"threshold_uncertainty_score":0.01432943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007272637217426041,"score_gpt":0.2655184055636998,"score_spread":0.2582457683462738,"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."}}