{"id":"W4310560843","doi":"10.48550/arxiv.2211.16991","title":"SparsePose: Sparse-View Camera Pose Regression and Refinement","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Computer vision; Pipeline (software); Pose; Fidelity; Object (grammar); Set (abstract data type); Camera resectioning; Pattern recognition (psychology)","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":[0.0009712462,0.001878556,0.001635537,0.001221853,0.0005256825,0.001510623,0.00272819,0.001711545,0.008011494],"category_scores_gemma":[0.004272265,0.001374635,0.001710789,0.001639177,0.0008951946,0.001975161,0.003175847,0.003642164,0.007819369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00058126,"about_ca_system_score_gemma":0.00142166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005955609,"about_ca_topic_score_gemma":0.01249779,"domain_scores_codex":[0.9988034,0.0001758185,0.00003521483,0.0003722217,0.0005124673,0.0001008805],"domain_scores_gemma":[0.9987878,0.0002787488,0.0001266764,0.0004648935,0.0002630572,0.00007890503],"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":[0.0002501529,0.000150438,0.001551704,0.0002662373,0.0001926061,0.0002577603,0.0002304956,0.1692972,0.03920764,0.01245009,0.0437632,0.7323825],"study_design_scores_gemma":[0.00003079394,0.00005031703,0.0005719825,0.00002411161,0.00001827526,0.0003091515,0.00004708613,0.9603099,0.01809784,0.008475993,0.01202787,0.00003663708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001281316,0.0001128802,0.992682,0.00007283764,0.00003167952,0.00003365186,0.0002145522,0.005032193,0.0005389071],"genre_scores_gemma":[0.0520246,0.0003988487,0.9388469,0.0002097166,0.00007630238,0.0001410127,0.003068004,0.001521184,0.003713397],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008011494,"threshold_uncertainty_score":0.02680111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0843943382238286,"score_gpt":0.225890700506514,"score_spread":0.1414963622826854,"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."}}