{"id":"W4377098794","doi":"10.21203/rs.3.rs-2946470/v1","title":"DMPH-Net: A Deep Multiscale Pyramid Hybrid Network for Low-Light Image Enhancement with Attention Mechanism and Noise Reduction","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"MD Precision (Canada)","funders":"","keywords":"Artificial intelligence; Fuse (electrical); Computer science; Pyramid (geometry); Computer vision; Brightness; Feature (linguistics); Noise (video); Noise reduction; Reduction (mathematics); Pattern recognition (psychology); Image (mathematics); Mathematics; Optics; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028862,0.000462411,0.0004719809,0.0005326243,0.0005978179,0.0009232163,0.001236101,0.0002253937,0.00001941102],"category_scores_gemma":[0.0001190713,0.0004322437,0.0001505368,0.000622884,0.0002042475,0.0006148842,0.002786096,0.0009936022,0.00006828617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004862279,"about_ca_system_score_gemma":0.0002174166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001201878,"about_ca_topic_score_gemma":0.00005137396,"domain_scores_codex":[0.9945354,0.0003864995,0.0005183297,0.001773931,0.001520555,0.001265279],"domain_scores_gemma":[0.9967452,0.0001664838,0.0002590198,0.001545688,0.001057449,0.0002261263],"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":[0.001550948,0.002586281,0.0003074122,0.01978522,0.001179354,0.0008728005,0.004744144,0.002204433,0.5630779,0.05895974,0.117781,0.2269508],"study_design_scores_gemma":[0.00199561,0.002501054,0.0009151429,0.005859009,0.00006886739,0.00005606167,0.0002679036,0.31397,0.5206901,0.1497091,0.002245635,0.001721518],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0132013,0.0003448014,0.9773937,0.002182344,0.0007037269,0.005125147,0.00003643305,0.0008451443,0.0001674252],"genre_scores_gemma":[0.4098775,0.001525724,0.5725753,0.00004786398,0.001279524,0.009336712,0.0004952514,0.0002158533,0.004646264],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4048184,"threshold_uncertainty_score":0.999813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03141243557161738,"score_gpt":0.3414934217926988,"score_spread":0.3100809862210814,"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."}}