{"id":"W4210419398","doi":"10.1109/tmi.2022.3147414","title":"A Robust Edge-Preserving Stereo Matching Method for Laparoscopic Images","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Foundation for Innovation","keywords":"Robustness (evolution); Stereoscopy; Matching (statistics); Feature extraction; Feature (linguistics); Specular highlight; Computer stereo vision; Stereo camera; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.001053276,0.0002149779,0.000273713,0.0002839887,0.001163822,0.0001983647,0.001322857,0.00002993719,0.000519987],"category_scores_gemma":[0.00005310389,0.0002177843,0.0001727718,0.0005003795,0.0000563125,0.0008236952,0.00005099612,0.0007977751,0.00001488299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001310246,"about_ca_system_score_gemma":0.0001395218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004905965,"about_ca_topic_score_gemma":0.000004594077,"domain_scores_codex":[0.9973322,0.0002470415,0.0003799706,0.0006481607,0.000860508,0.000532115],"domain_scores_gemma":[0.9983112,0.0006767902,0.00009442898,0.0005747992,0.00006498987,0.0002778503],"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":[0.00002461624,0.0002213547,0.00001063141,0.00005511208,0.00002952261,0.00005619372,0.0009649166,0.03899326,0.004365013,0.0004806428,0.002434565,0.9523641],"study_design_scores_gemma":[0.001129108,0.00004697166,0.000008971266,0.00008398202,0.00001680936,0.0001194025,0.0005670011,0.9789536,0.008511076,0.002884889,0.007395136,0.0002830602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001513027,0.0001436954,0.9879054,0.00886279,0.001851115,0.0002775116,0.00001622992,0.0003899813,0.0004019599],"genre_scores_gemma":[0.1231375,0.00002738853,0.8678905,0.007436157,0.0001286782,0.0003582328,0.000003205091,0.00005391387,0.0009644379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9520811,"threshold_uncertainty_score":0.89513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02766361089645171,"score_gpt":0.3274611001062153,"score_spread":0.2997974892097636,"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."}}