{"id":"W4361855244","doi":"10.1109/icpeca56706.2023.10075875","title":"End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volume","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Benchmark (surveying); Metric (unit); Convolutional neural network; Structure from motion; Computer vision; Matching (statistics); Volume (thermodynamics); Feature (linguistics); Range (aeronautics); Deep learning; 3D reconstruction; Virtual reality; Iterative reconstruction; Solid modeling; Motion (physics); Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008183071,0.0001122005,0.0001076302,0.000129631,0.0001121149,0.0001086588,0.000309478,0.00002824047,0.0002456595],"category_scores_gemma":[0.00003177638,0.00008505695,0.00002365234,0.0007755365,0.00001643686,0.0007809128,0.0001480915,0.00009899834,0.0008815748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003086353,"about_ca_system_score_gemma":0.00002032691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005584922,"about_ca_topic_score_gemma":0.00004199588,"domain_scores_codex":[0.9990004,0.00002874027,0.0001389347,0.0003774644,0.000246205,0.0002082402],"domain_scores_gemma":[0.999399,0.00003436283,0.00003923802,0.0003655293,0.00006231714,0.00009953284],"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":[0.000003843786,0.00001710656,0.004965462,0.000005480025,0.000007153434,0.00001140692,0.0005814576,0.003344149,0.004083933,0.002946398,0.001297671,0.9827359],"study_design_scores_gemma":[0.0003287168,0.00004157514,0.09860098,0.00002971104,0.000003690664,0.000007609372,0.00005776712,0.8860484,0.001065346,0.001020522,0.01260213,0.0001935303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01432949,0.00002327371,0.982869,0.001276163,0.0003085884,0.0001341551,0.000003842613,0.0004964085,0.0005590339],"genre_scores_gemma":[0.6110055,0.000007698557,0.3857637,0.0007150258,0.0000392993,0.000004091253,0.00001961244,0.00001048402,0.002434552],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825424,"threshold_uncertainty_score":0.9998963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01925208741275214,"score_gpt":0.2722407113541249,"score_spread":0.2529886239413727,"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."}}