{"id":"W2130905995","doi":"10.1109/83.869183","title":"Bayesian winner-take-all reconstruction of intermediate views from stereoscopic images","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Maximum a posteriori estimation; Artificial intelligence; Iterative reconstruction; Probabilistic logic; Stereoscopy; Computer vision; Computer science; Binary number; Algorithm; Expectation–maximization algorithm; Field (mathematics); Mathematics; Maximum likelihood","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":[0.0001139552,0.0002211013,0.0002733817,0.0002064984,0.0001998779,0.0002141008,0.0004636498,0.00005787431,0.0004327478],"category_scores_gemma":[0.000004950997,0.0002105306,0.0001059161,0.0003971007,0.0001499008,0.002274174,0.000003167873,0.0002979102,0.00007645246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004968196,"about_ca_system_score_gemma":0.00006516765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002751812,"about_ca_topic_score_gemma":0.000008902304,"domain_scores_codex":[0.9984255,0.00007368583,0.0004779432,0.0005013135,0.000236782,0.0002848009],"domain_scores_gemma":[0.9991335,0.0000553813,0.0001740627,0.0004322438,0.0000961019,0.0001086663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001834852,0.0000737185,0.0000117756,0.00003169513,0.00001074643,0.000004621982,0.0006063696,0.0001573335,0.02746164,0.000001417572,0.00002619848,0.9715961],"study_design_scores_gemma":[0.001883504,0.0002343179,0.0008332045,0.001416025,0.0000758299,0.00008503201,0.0003723231,0.3560311,0.6336997,0.003066069,0.00146483,0.0008381245],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01078834,0.0002066962,0.9865541,0.0002169299,0.0004342111,0.0001352919,0.00001533139,0.000214345,0.001434739],"genre_scores_gemma":[0.721603,0.0001093946,0.2774945,0.0003115024,0.00004294434,0.00001505786,0.000001657234,0.00002099895,0.0004010159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.970758,"threshold_uncertainty_score":0.8585191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01822952861477366,"score_gpt":0.2829056101124984,"score_spread":0.2646760814977247,"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."}}