{"id":"W2175816919","doi":"10.1109/3dv.2015.53","title":"Multiscale Retinex Aggregation to Enable Robust Dense Stereo Correspondence","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Artificial intelligence; Benchmark (surveying); Computer vision; Computer science; Color constancy; Matching (statistics); Stereopsis; Texture (cosmology); Stereo cameras; Computer stereo vision; Contrast (vision); Image (mathematics); Mathematics","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":[0.0007727874,0.0005974316,0.0009478402,0.001363384,0.000398059,0.0008482804,0.0007050678,0.0005263165,0.002117486],"category_scores_gemma":[0.001817602,0.0003309235,0.0009420468,0.001006852,0.0003888225,0.0009501722,0.001718055,0.0006820793,0.000529898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004970595,"about_ca_system_score_gemma":0.0005509589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001458064,"about_ca_topic_score_gemma":0.002096615,"domain_scores_codex":[0.999182,0.0001350032,0.00004078839,0.0001213075,0.0004452935,0.0000756173],"domain_scores_gemma":[0.9992386,0.0001867279,0.00009731892,0.0002827785,0.0001607488,0.00003387698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002732192,0.0001769515,0.00160179,0.000148763,0.0001484855,0.0002770548,0.0003176312,0.2487414,0.2222544,0.03883868,0.004242116,0.4829795],"study_design_scores_gemma":[0.00002135844,0.00007630377,0.001018692,0.00001089479,0.00003195676,0.0002781452,0.00003556064,0.9426862,0.04269637,0.00874574,0.004373105,0.0000257066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01904957,0.0000977416,0.9789695,0.00003973098,0.00001930244,0.00002752667,0.00003896813,0.0004171846,0.001340442],"genre_scores_gemma":[0.2962061,0.0001806976,0.7013691,0.0000852386,0.00005604127,0.00006798705,0.0001466638,0.0001436242,0.001744438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002117486,"threshold_uncertainty_score":0.007083714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05405489983684779,"score_gpt":0.2936717224001816,"score_spread":0.2396168225633338,"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."}}