{"id":"W2754329383","doi":"10.1109/lra.2017.2778765","title":"DPC-Net: Deep Pose Correction for Visual Localization","year":2017,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Odometry; Artificial intelligence; Visual odometry; Computer science; Estimator; Ground truth; Pose; Deep learning; Pipeline (software); Computer vision; Convolutional neural network; Rotation (mathematics); Translation (biology); Pattern recognition (psychology); Algorithm; Mathematics; Robot; Mobile robot","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":[0.0005187409,0.001575422,0.0006813805,0.0008283167,0.0004602256,0.0009065364,0.003007035,0.001234581,0.004783755],"category_scores_gemma":[0.001839407,0.0006497517,0.0005650554,0.0007370173,0.0007846544,0.001420253,0.00240339,0.002224248,0.002100479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001147783,"about_ca_system_score_gemma":0.001415412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009446315,"about_ca_topic_score_gemma":0.01598418,"domain_scores_codex":[0.9996321,0.00003297222,0.00001164169,0.0001252814,0.0001487582,0.00004923611],"domain_scores_gemma":[0.9995739,0.00007779671,0.00005950733,0.0001370012,0.0001133768,0.00003851334],"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":[0.0001955266,0.0001428843,0.001762593,0.0001078657,0.0001183516,0.0001527742,0.00006616766,0.355001,0.01804404,0.0156835,0.02168754,0.5870377],"study_design_scores_gemma":[0.00001170982,0.00003843634,0.0002329792,0.000009607234,0.00001001604,0.00004893578,0.000008439833,0.9794373,0.01017016,0.005829141,0.004192192,0.0000111532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006326876,0.0001141158,0.9836571,0.0001317233,0.0001176375,0.00003840186,0.0003002991,0.007628562,0.001685294],"genre_scores_gemma":[0.3088913,0.0002245735,0.6742148,0.0004995597,0.0001290645,0.0002615273,0.002481744,0.001047866,0.01224959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009446315,"threshold_uncertainty_score":0.01878268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296846921203959,"score_gpt":0.2900750068234628,"score_spread":0.2771065376114232,"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."}}