{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001759878,0.0001181606,0.0001142662,0.0002928579,0.00003456093,0.00005286925,0.00004327142,0.00007875109,0.000005708575],"category_scores_gemma":[0.0000446755,0.0001327308,0.00002215202,0.000366181,0.000008031048,0.0001046095,0.00001094062,0.0001599656,0.000004863984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005249771,"about_ca_system_score_gemma":0.000007874242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001248133,"about_ca_topic_score_gemma":0.000008877564,"domain_scores_codex":[0.9994382,0.00001142038,0.0001650963,0.0001253412,0.00008729047,0.0001726415],"domain_scores_gemma":[0.9997328,0.00008308649,0.00001043447,0.0001067051,0.0000178608,0.00004912921],"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":[0.00001067654,0.00002505608,0.000293178,0.0001584215,0.000008088879,0.000001824081,0.0000657068,0.9485279,0.04865425,0.001489199,0.00007449026,0.0006912334],"study_design_scores_gemma":[0.0003947111,0.00002444406,0.0008117707,0.00006999233,0.000009680743,2.937297e-7,0.00007906498,0.9859372,0.01198297,0.00002622027,0.0005376718,0.0001259691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09626032,0.00007476868,0.9008122,0.00009173914,0.0003080697,0.0001064418,0.0000109843,0.0001378238,0.002197642],"genre_scores_gemma":[0.8203365,0.0001118352,0.1791821,0.0001457902,0.00004295809,0.0000199903,0.00005206452,0.0000343514,0.00007443967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7240762,"threshold_uncertainty_score":0.5412605,"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."}}