{"id":"W2796635488","doi":"10.1109/cvprw.2018.00064","title":"Geometric Consistency for Self-Supervised End-to-End Visual Odometry","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Compute Canada; Nvidia","keywords":"Visual odometry; Artificial intelligence; Odometry; Computer science; Deep learning; Ground truth; Computer vision; Leverage (statistics); Inertial measurement unit; Global Positioning System; Geometric transformation; Consistency (knowledge bases); Pipeline (software); Robot; Mobile robot; Image (mathematics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006701541,0.0004731684,0.0006136618,0.001735506,0.0002538107,0.000526124,0.002158872,0.0002300166,0.0004168538],"category_scores_gemma":[0.0005587012,0.0004285439,0.0003311622,0.001897045,0.00007089904,0.0004192393,0.003793872,0.0004098755,0.0004519951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001575042,"about_ca_system_score_gemma":0.0003553435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002254883,"about_ca_topic_score_gemma":0.000002173188,"domain_scores_codex":[0.9964892,0.000068633,0.0006229825,0.001492374,0.0006194934,0.0007073691],"domain_scores_gemma":[0.9968447,0.0005414097,0.0002092552,0.001415599,0.0005792447,0.000409796],"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":[0.00002681503,0.0004661834,0.0004690267,0.0003795588,0.000177062,0.00001837465,0.0005917535,0.00007807232,0.0005292561,0.00892903,0.02605457,0.9622803],"study_design_scores_gemma":[0.002048343,0.0008310422,0.001805085,0.0002632053,0.00008142585,0.00004370982,0.0001459481,0.8397847,0.007138009,0.01530594,0.1302555,0.002297093],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001825842,0.000297481,0.9814742,0.001053678,0.00249981,0.0009838723,0.00002192849,0.0008537002,0.01098944],"genre_scores_gemma":[0.08709784,0.0000560189,0.90776,0.002954274,0.0004016959,0.0001150737,0.00002226451,0.00004388504,0.001548945],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9599832,"threshold_uncertainty_score":0.9998167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03108524117707117,"score_gpt":0.3283328860788092,"score_spread":0.297247644901738,"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."}}