{"id":"W4319160422","doi":"10.3390/s23031650","title":"Efficient Stereo Depth Estimation for Pseudo-LiDAR: A Self-Supervised Approach Based on Multi-Input ResNet Encoder","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"University of Ontario Institute of Technology","keywords":"Lidar; Point cloud; Estimator; Computer science; Benchmark (surveying); Computer vision; Artificial intelligence; Depth map; Stereopsis; Point (geometry); Encoder; Depth perception; Measured depth; Remote sensing; Image (mathematics); Perception; Geology; Mathematics; Geodesy","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":[0.0003801146,0.0002005833,0.0001853508,0.0002829285,0.0002187548,0.0001301396,0.0004184366,0.0000578106,0.000003317349],"category_scores_gemma":[0.0001731893,0.0001774334,0.000103477,0.0006867911,0.00002540099,0.0001041616,0.00009634128,0.0001267054,0.0001304846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006348923,"about_ca_system_score_gemma":0.00005392185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004280825,"about_ca_topic_score_gemma":0.000001090963,"domain_scores_codex":[0.9982547,0.00008323514,0.0002605094,0.0006000875,0.0003742943,0.0004271333],"domain_scores_gemma":[0.9988641,0.0002059651,0.00008113209,0.0006220362,0.0001032596,0.0001234738],"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":[0.0000259151,0.0001983126,0.00006733304,0.00005766358,0.000008605273,0.000008451433,0.001377801,0.9352872,0.000459827,0.0005381996,0.0005470859,0.06142356],"study_design_scores_gemma":[0.001259499,0.00008027658,0.0009271014,0.00003387725,0.000005812563,0.000003250842,0.000103331,0.9958906,0.0009142524,0.00007250915,0.000486288,0.0002232483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05442646,0.000005559141,0.9424639,0.0006537143,0.0002612032,0.0005947079,0.000007541868,0.0008694732,0.0007174782],"genre_scores_gemma":[0.3200803,0.000001001311,0.6789777,0.0006254999,0.00002842902,0.00004287841,0.00001785647,0.00002175873,0.0002046188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2656538,"threshold_uncertainty_score":0.7235522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03604234561636074,"score_gpt":0.3019441228024621,"score_spread":0.2659017771861014,"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."}}