{"id":"W3020512542","doi":"10.1109/cvprw50498.2020.00028","title":"Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"International Institute of Information Technology, Hyderabad","keywords":"Artificial intelligence; Computer vision; Computer science; Rendering (computer graphics); Leverage (statistics); Monocular; Differentiable function; Object (grammar); Deep neural networks; Deep learning; 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":[0.0005688936,0.001270822,0.0008651139,0.0006936223,0.0004229016,0.00107165,0.001730766,0.001233609,0.004814895],"category_scores_gemma":[0.001859599,0.0009556013,0.0007931122,0.0006955045,0.0009116542,0.001465593,0.002261094,0.001897906,0.002349811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005128762,"about_ca_system_score_gemma":0.001219244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005520755,"about_ca_topic_score_gemma":0.008489389,"domain_scores_codex":[0.9996054,0.00004069926,0.00001233906,0.0001342143,0.0001680568,0.00003933108],"domain_scores_gemma":[0.999542,0.0001113934,0.00005126255,0.0001924667,0.00006514199,0.00003779323],"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":[0.0003241486,0.0001229774,0.001325287,0.0001995017,0.0001742313,0.0003064435,0.0002468553,0.2422687,0.04439175,0.01826617,0.01570013,0.6766738],"study_design_scores_gemma":[0.00002052961,0.00004697232,0.0003221365,0.00001437193,0.00001509364,0.0002175079,0.00002939758,0.9683731,0.01557662,0.008334469,0.007024112,0.00002577074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004138237,0.00007059766,0.9903566,0.00009137105,0.00003098842,0.0000263356,0.0001133165,0.004319114,0.0008533511],"genre_scores_gemma":[0.09605166,0.0002009016,0.8975217,0.0002004555,0.00005556863,0.00009945541,0.0008404998,0.001167907,0.003861687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005520755,"threshold_uncertainty_score":0.01610744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02881512872024633,"score_gpt":0.2669982046065049,"score_spread":0.2381830758862585,"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."}}