{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007807837,0.0001940904,0.0002582242,0.0001564209,0.0001227475,0.00005589367,0.0007579454,0.00007564126,0.00002945384],"category_scores_gemma":[0.00002306903,0.0002086569,0.00009005367,0.0004540514,0.00009049979,0.0004489139,0.000814184,0.0005043092,0.00002489534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007821662,"about_ca_system_score_gemma":0.000145707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003464153,"about_ca_topic_score_gemma":0.000001749681,"domain_scores_codex":[0.9988056,0.00009987225,0.0001611984,0.0006447088,0.0001231928,0.0001654335],"domain_scores_gemma":[0.9989436,0.00007510241,0.0002492373,0.0004321742,0.0001819039,0.0001180179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006875884,0.00006052927,0.00149849,0.00009030785,0.00005101192,0.0001581854,0.000464345,0.9326529,0.000719792,0.06136278,0.00008114496,0.002791767],"study_design_scores_gemma":[0.000470492,0.00009726274,0.001340065,0.0001792991,0.0000252523,0.000004488609,0.00008375233,0.9876678,0.0004988232,0.009281638,0.000114146,0.000236971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04881788,0.00002310496,0.9488704,0.0003888512,0.0001000856,0.000137357,0.000005334357,0.0001714439,0.001485508],"genre_scores_gemma":[0.9306486,0.00002573669,0.06898397,0.0001393119,0.00002202572,3.030473e-7,0.00003492451,0.0000113946,0.0001337444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8818307,"threshold_uncertainty_score":0.8508782,"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."}}