{"id":"W2999318879","doi":"10.48550/arxiv.2001.06479","title":"Unsupervised Learning of Camera Pose with Compositional Re-estimation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Artificial intelligence; Computer vision; Computer science; Camera auto-calibration; Benchmark (surveying); Motion estimation; Pose; Camera resectioning; Transformation (genetics); Process (computing); Optical flow; Motion (physics); Pixel; Image (mathematics); Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006718388,0.002040918,0.001795494,0.001460348,0.0004652814,0.001152985,0.002262134,0.001287919,0.001946376],"category_scores_gemma":[0.003248717,0.001070333,0.001525634,0.00163423,0.0008940844,0.001746887,0.00176097,0.002050314,0.001681601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006584567,"about_ca_system_score_gemma":0.00121546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006066779,"about_ca_topic_score_gemma":0.01303994,"domain_scores_codex":[0.9989426,0.0001803061,0.00003747724,0.000527172,0.0001977361,0.0001148016],"domain_scores_gemma":[0.9988493,0.000278709,0.0001910566,0.0003624436,0.0002517264,0.00006674571],"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":[0.0002443169,0.0002254314,0.002981938,0.0002548578,0.0002683934,0.0002452614,0.0002238168,0.329571,0.03798738,0.005841702,0.007237074,0.6149188],"study_design_scores_gemma":[0.00001258169,0.00004801196,0.0007311603,0.00001433634,0.00002372889,0.0001175482,0.00002450729,0.983648,0.008153806,0.005627889,0.001578494,0.00001985863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01226931,0.0002633092,0.9847023,0.00007134359,0.00003791076,0.00005672628,0.0001375196,0.001757297,0.0007042468],"genre_scores_gemma":[0.3561853,0.0006704512,0.6338528,0.000313321,0.000212504,0.0002022488,0.002637681,0.0006819597,0.005243618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006066779,"threshold_uncertainty_score":0.01206291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05820510733924513,"score_gpt":0.202781948028666,"score_spread":0.1445768406894208,"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."}}