{"id":"W3116856723","doi":"10.1109/access.2020.3047074","title":"Multispectral Image Reconstruction From Color Images Using Enhanced Variational Autoencoder and Generative Adversarial Network","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); McGill University; École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multispectral image; Autoencoder; Artificial intelligence; Computer science; Computer vision; Adversarial system; Iterative reconstruction; Image (mathematics); Generative grammar; Image restoration; Pattern recognition (psychology); Image processing; Deep learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00100369,0.001188343,0.0008495633,0.0007982715,0.0002256043,0.0008074948,0.001183807,0.001003129,0.001395575],"category_scores_gemma":[0.001687845,0.0005061429,0.001313587,0.0006260271,0.0006934316,0.0008335217,0.001052617,0.001966231,0.0005632371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007175995,"about_ca_system_score_gemma":0.0006201746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005448481,"about_ca_topic_score_gemma":0.007334157,"domain_scores_codex":[0.9995474,0.0001193684,0.00001666611,0.0001285666,0.0001423537,0.00004551551],"domain_scores_gemma":[0.9995109,0.000201767,0.00005288407,0.0001109578,0.00009384181,0.00002961629],"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":[0.0001416646,0.0000789297,0.0008374549,0.00008530047,0.0001390145,0.0001312195,0.0000582262,0.8408967,0.01337279,0.008248587,0.002836079,0.133174],"study_design_scores_gemma":[0.000003288169,0.000007680606,0.00006498265,0.000003641098,0.000004367984,0.00002275693,0.000002969579,0.9964934,0.001533841,0.001525894,0.000333219,0.00000401779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0149048,0.0003979829,0.9817869,0.0002325256,0.00005167666,0.00003832044,0.0001229165,0.001031558,0.001433379],"genre_scores_gemma":[0.4430582,0.0006765533,0.5476564,0.0005376656,0.0001038112,0.0001057995,0.001384576,0.0004643555,0.006012569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005448481,"threshold_uncertainty_score":0.01083356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04307780010512747,"score_gpt":0.3136450972767429,"score_spread":0.2705672971716154,"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."}}