{"id":"W4416424927","doi":"10.1016/j.neucom.2025.132113","title":"Boosting monocular depth estimation with semantic diffusion guided convolutional transformer model","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Residual; Depth map; Monocular; Transformer; Smoothing; Segmentation; Boosting (machine learning); Inference","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":[0.0001616906,0.0001742928,0.0001661003,0.0001635595,0.0004180903,0.0001381119,0.0003876015,0.00003314815,0.000001255375],"category_scores_gemma":[0.00005202708,0.0001540269,0.00005348771,0.0004730934,0.00003383163,0.0005277554,0.000126936,0.0001940468,0.0000071318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004369647,"about_ca_system_score_gemma":0.00009631644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007004352,"about_ca_topic_score_gemma":0.000001305499,"domain_scores_codex":[0.998588,0.00003962331,0.000305565,0.0004678748,0.0002774245,0.0003215266],"domain_scores_gemma":[0.9993533,0.000105034,0.00009653757,0.0002795429,0.000103801,0.00006180469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008189227,0.00004883131,0.001302189,0.00005226077,0.000009836221,0.0000136461,0.0002750438,0.5512663,0.0112711,0.01065182,0.000136014,0.4249648],"study_design_scores_gemma":[0.000565881,0.00002115892,0.002273218,0.0001852907,0.000008079656,0.00002814083,0.000009959356,0.9917819,0.002114061,0.002705869,0.0001501862,0.0001562856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03162241,0.0000456601,0.9639001,0.0008450953,0.0001186258,0.0002133762,2.506166e-7,0.0003092868,0.002945154],"genre_scores_gemma":[0.5803946,0.000002203687,0.4186302,0.0008606187,0.0000132306,0.00000391861,0.000001715035,0.000007895153,0.00008559343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5487722,"threshold_uncertainty_score":0.6281033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01553985954031968,"score_gpt":0.2809593742617487,"score_spread":0.2654195147214291,"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."}}