{"id":"W4411438078","doi":"10.1016/j.optlaseng.2025.109174","title":"Full-stokes image restoration method based on large-scale sub-pixel segmentation","year":2025,"lang":"en","type":"article","venue":"Optics and Lasers in Engineering","topic":"Optical Polarization and Ellipsometry","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Natural Science Foundation of Guangdong Province; St. Thomas University","keywords":"Computer science; Pixel; Computer vision; Scale (ratio); Artificial intelligence; Segmentation; Image (mathematics); Image segmentation; Image restoration; Image processing; Cartography; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004302336,0.0007643918,0.0009283269,0.001076448,0.0005202861,0.001008139,0.0007729535,0.0007751357,0.003058766],"category_scores_gemma":[0.0007810706,0.0004970585,0.0009352762,0.0008287308,0.0005102362,0.001142725,0.0008205414,0.0008471305,0.001304129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003942399,"about_ca_system_score_gemma":0.001488428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003166009,"about_ca_topic_score_gemma":0.004563969,"domain_scores_codex":[0.9996616,0.00003346055,0.00002053946,0.00007437656,0.0001699562,0.00004015898],"domain_scores_gemma":[0.9996932,0.00004898764,0.00003022027,0.00007597375,0.0001339704,0.00001769219],"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":[0.0003866442,0.0001308606,0.0014367,0.0002985847,0.000113186,0.0001263071,0.0002724201,0.06449165,0.1922997,0.01210075,0.006038923,0.7223043],"study_design_scores_gemma":[0.00001550992,0.00004667423,0.001157156,0.00001502072,0.00004560559,0.0002007938,0.00004537549,0.9341879,0.05285577,0.004043305,0.007353918,0.00003293782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01521704,0.0002776258,0.9807848,0.0001371844,0.00007599152,0.00004667792,0.00009142231,0.001183029,0.002186326],"genre_scores_gemma":[0.1290358,0.0004819966,0.8644017,0.0001050916,0.00005796071,0.00007970579,0.0005099354,0.0004142791,0.004913487],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003166009,"threshold_uncertainty_score":0.01023257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003764489858774825,"score_gpt":0.2296542675068255,"score_spread":0.2258897776480507,"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."}}