{"id":"W3170812607","doi":"10.1109/cvpr46437.2021.00880","title":"Differentiable Diffusion for Dense Depth Estimation from Multi-view Images","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Outlier; Computer science; Artificial intelligence; Reprojection error; Computer vision; RGB color model; Depth map; Ground truth; Deep learning; Point (geometry); Set (abstract data type); Differentiable function; Algorithm; Image (mathematics); 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":[0.0007584499,0.001124182,0.0008903676,0.0007617413,0.000389805,0.0007877245,0.001318296,0.001220078,0.002075351],"category_scores_gemma":[0.003057187,0.0007520674,0.0006860298,0.000776175,0.0009588228,0.00148907,0.00173853,0.001801192,0.0007088708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001753898,"about_ca_system_score_gemma":0.001237408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007982608,"about_ca_topic_score_gemma":0.01074441,"domain_scores_codex":[0.9994899,0.00008166565,0.00002137482,0.0001241827,0.0002398758,0.00004300383],"domain_scores_gemma":[0.9994211,0.0001889166,0.00009436679,0.000128398,0.0001243134,0.00004300005],"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":[0.0001504798,0.00006484324,0.0007297515,0.0001789608,0.00008875284,0.00009634553,0.0001613544,0.7106183,0.05227781,0.02541931,0.003504473,0.2067096],"study_design_scores_gemma":[0.000007463159,0.00001018221,0.00009330991,0.000004807333,0.000002840779,0.0000281557,0.000004269512,0.9899824,0.004475684,0.004659762,0.0007246177,0.000006546582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003907441,0.0001024855,0.9949818,0.0001064563,0.00001058705,0.00001394147,0.00004727968,0.0005126212,0.0003173888],"genre_scores_gemma":[0.1837746,0.0002667503,0.8125727,0.0001257129,0.00004652614,0.00009923617,0.0003181095,0.0004181714,0.002378157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007982608,"threshold_uncertainty_score":0.0158723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03598565101548167,"score_gpt":0.3235970494422183,"score_spread":0.2876113984267367,"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."}}