{"id":"W3138194750","doi":"10.1007/s00371-021-02087-5","title":"A robust framework for multi-view stereopsis","year":2021,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"","keywords":"Point cloud; Computer science; Artificial intelligence; Stereopsis; Outlier; Computer vision; Matching (statistics); Point (geometry); Computer graphics; Scalability; Polygon mesh; Stereo cameras; Artificial neural network; Point set registration; Computer graphics (images); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002064525,0.0001424848,0.0001790387,0.00003526582,0.0002334063,0.0002803588,0.000715745,0.00004056466,0.00002402438],"category_scores_gemma":[0.00004935925,0.00009902334,0.0001221775,0.0003566302,0.0000358853,0.0002748454,0.0006144635,0.0001723711,0.00008203772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001889856,"about_ca_system_score_gemma":0.00004468935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001314064,"about_ca_topic_score_gemma":0.000001148907,"domain_scores_codex":[0.9988613,0.00009377224,0.0001967694,0.0003871218,0.0001642916,0.0002968006],"domain_scores_gemma":[0.9988224,0.0003295592,0.00006488225,0.0005662784,0.0001429779,0.0000738978],"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":[0.000006361084,0.0001597685,0.00005750802,0.00003354308,0.00003217881,0.00001714169,0.0008022698,0.0005829466,0.0001194968,0.06455678,0.002108696,0.9315233],"study_design_scores_gemma":[0.0003511646,0.00006534014,0.0005034177,0.00009415065,0.000006487674,0.00002776415,0.00002558201,0.9675437,0.001099288,0.007007475,0.02309199,0.0001836785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007102659,0.0004127783,0.99519,0.002495637,0.0008179711,0.0001707038,0.000001454052,0.0001538227,0.00004742627],"genre_scores_gemma":[0.01395687,0.00002528488,0.9783105,0.007087979,0.0002845283,0.00001819553,0.000002273557,0.0000148413,0.0002994799],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9669607,"threshold_uncertainty_score":0.4038055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125116658792412,"score_gpt":0.378968371257991,"score_spread":0.2664567053787498,"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."}}