{"id":"W2057165790","doi":"10.5594/j18043xy","title":"A Nonconventional Approach to the Conversion of 2D Video and Film Content to Stereoscopic 3D","year":2011,"lang":"en","type":"article","venue":"SMPTE Motion Imaging Journal","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Stereoscopy; Computer science; Artificial intelligence; Computer vision; 2D to 3D conversion; Projection (relational algebra); Task (project management); Realization (probability); Computer graphics (images); Depth map; Image (mathematics); Mathematics; Algorithm; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0005195033,0.0001074596,0.0001311435,0.0001869974,0.0002220867,0.0001279399,0.0004394363,0.0000132301,0.00004856973],"category_scores_gemma":[0.00005373219,0.00007724724,0.00005788308,0.0002069459,0.00004793581,0.0006166614,0.0002507826,0.0001825785,0.00002892108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003976022,"about_ca_system_score_gemma":0.00002810445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001406827,"about_ca_topic_score_gemma":3.13685e-7,"domain_scores_codex":[0.9988886,0.00008404726,0.0002926635,0.0002313599,0.0002984308,0.0002049012],"domain_scores_gemma":[0.9991769,0.00002579309,0.0001527573,0.0002356507,0.000217505,0.0001914005],"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":[0.0001734671,0.0007124578,0.09203172,0.0001420868,0.0001213332,0.0000457369,0.02534112,0.0007039585,0.01488338,0.01241298,0.0161573,0.8372745],"study_design_scores_gemma":[0.004789885,0.0005570345,0.4446797,0.0009352107,0.00006653449,0.002067394,0.00351336,0.4908936,0.01594877,0.003509735,0.03207037,0.0009683854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01242065,0.0001268949,0.9835247,0.001779304,0.0004886281,0.0001560321,0.000001653058,0.00002432079,0.001477861],"genre_scores_gemma":[0.7009727,0.00001431716,0.2968638,0.001821644,0.00007223056,0.000004790817,6.680948e-7,0.000007756644,0.0002420897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8363061,"threshold_uncertainty_score":0.3150051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04868451064072576,"score_gpt":0.2563578777559411,"score_spread":0.2076733671152153,"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."}}