{"id":"W4321854081","doi":"10.48550/arxiv.2302.11683","title":"MVTrans: Multi-View Perception of Transparent Objects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Computer vision; Computer science; RGB color model; Pipeline (software); Pose; Perception; Segmentation; Object (grammar); Robot; Depth perception; Object detection","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":[0.0004426189,0.001839198,0.0008933176,0.0009706574,0.0003794006,0.001169197,0.002387166,0.001144615,0.004315233],"category_scores_gemma":[0.001439257,0.0008457691,0.001489084,0.000603521,0.0004889673,0.001988604,0.002936077,0.001852779,0.003205395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004783686,"about_ca_system_score_gemma":0.0006699312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006192406,"about_ca_topic_score_gemma":0.01230485,"domain_scores_codex":[0.999348,0.00005665988,0.00001424211,0.0003128353,0.0001878795,0.00008036052],"domain_scores_gemma":[0.9994937,0.00006714775,0.00004714056,0.0002333976,0.00009123798,0.00006732113],"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":[0.0008529674,0.0005583767,0.004674248,0.000806164,0.0003481811,0.0006010886,0.0003402174,0.06403127,0.1458426,0.005709146,0.1052036,0.6710322],"study_design_scores_gemma":[0.00008186119,0.0004162243,0.007373443,0.000118191,0.00006865133,0.0007853545,0.0001746873,0.8598491,0.0754186,0.01101289,0.04461551,0.00008552805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08408674,0.001170719,0.8400243,0.0003806188,0.0004733687,0.0004046141,0.01930307,0.04600759,0.008148948],"genre_scores_gemma":[0.3158049,0.0006914359,0.6128983,0.0004822148,0.0001160235,0.0003470258,0.05919914,0.00213099,0.008329964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006192406,"threshold_uncertainty_score":0.01443589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.20160315753118,"score_gpt":0.2506157285634101,"score_spread":0.04901257103223006,"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."}}