{"id":"W2051938740","doi":"10.1109/icip.2012.6467528","title":"Radiometric invariant stereo matching based on relative gradients","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Weighting; Pixel; Invariant (physics); Computer vision; Computer science; Gaussian; Matching (statistics); Limiting; Range (aeronautics); Stereopsis; Boundary (topology); Gaussian function; Mathematics; Statistics","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":[0.0003053558,0.0001040645,0.0001010822,0.0004420415,0.0001132001,0.00007318486,0.0003726402,0.00002147995,0.00005474309],"category_scores_gemma":[0.0000721636,0.00007987374,0.00004187903,0.001076099,0.00001337935,0.001468556,0.0001172554,0.0001315174,0.0002820106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006220481,"about_ca_system_score_gemma":0.0000141351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000865221,"about_ca_topic_score_gemma":2.112257e-7,"domain_scores_codex":[0.9990143,0.00006145786,0.0001386643,0.0002120426,0.0002556539,0.0003178859],"domain_scores_gemma":[0.9991985,0.0001936192,0.00005712605,0.0003676686,0.00002356453,0.000159513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001788812,0.000536609,0.01114153,0.00001492717,0.00002252327,0.0000197029,0.00265264,0.0006897721,0.0008983884,0.5788036,0.001686782,0.4035156],"study_design_scores_gemma":[0.001710286,0.0002112527,0.04813769,0.00009827151,0.000007691051,0.00002275937,0.0001089068,0.9213449,0.003396254,0.01365197,0.01066086,0.0006491499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002640517,0.0000428042,0.9697224,0.0004903628,0.0004424316,0.00008081885,3.132444e-7,0.0001385763,0.02644175],"genre_scores_gemma":[0.7454952,0.000001519153,0.2520738,0.001872124,0.00003071267,0.000002646701,6.333781e-7,0.000005900348,0.0005174707],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9206551,"threshold_uncertainty_score":0.3624769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02688364338897416,"score_gpt":0.2849179702891164,"score_spread":0.2580343269001423,"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."}}