{"id":"W2109709654","doi":"10.1109/cvpr.2005.168","title":"Geo-Consistency for Wide Multi-Camera Stereo","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; University of Tsukuba","keywords":"Artificial intelligence; Computer vision; Computer science; Matching (statistics); Depth map; Computation; Epipolar geometry; Visibility; Stereo camera; Stereopsis; Consistency (knowledge bases); Cut; Convergence (economics); Graph; Image (mathematics); Mathematics; Algorithm; Image segmentation; Geography; Theoretical computer science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089507,0.0000860682,0.00009477472,0.00005136548,0.0001046407,0.0000820475,0.0003905031,0.0000181261,0.00004768193],"category_scores_gemma":[0.0000561732,0.00007089406,0.00006003474,0.00009944572,0.00002100282,0.0006890855,0.00008292719,0.00005126863,0.0001641296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001941687,"about_ca_system_score_gemma":0.00002437695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005446973,"about_ca_topic_score_gemma":0.00001259244,"domain_scores_codex":[0.9992502,0.000009842882,0.0001591416,0.0002626911,0.00009070204,0.0002273972],"domain_scores_gemma":[0.9993801,0.00009806328,0.00003784738,0.0003471287,0.00006116583,0.00007573126],"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":[0.000002235723,0.00005518281,0.0002286312,0.00000353846,0.000004185396,0.000001074174,0.0001649645,0.0000394194,0.0008924471,0.02049431,0.003547808,0.9745662],"study_design_scores_gemma":[0.0009553261,0.00003919381,0.001046215,0.00001310616,0.000002377441,0.000008894149,0.00004886016,0.7080947,0.007847151,0.001972523,0.2797504,0.0002213057],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003024332,0.0001171259,0.9882477,0.006116029,0.000139123,0.0001417006,7.221425e-7,0.0001905871,0.004744587],"genre_scores_gemma":[0.1022853,0.000008034211,0.8868532,0.005273321,0.00004521475,0.00001252168,4.920631e-7,0.000006261405,0.005515593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9743449,"threshold_uncertainty_score":0.2890976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03186549094112291,"score_gpt":0.3102929866614789,"score_spread":0.278427495720356,"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."}}