{"id":"W2120221363","doi":"10.1109/iccv.2007.4408898","title":"A Layer-Based Restoration Framework for Variable-Aperture Photography","year":2007,"lang":"en","type":"article","venue":"","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Alfred P. Sloan Foundation","keywords":"Computer vision; Computational photography; Computer science; Artificial intelligence; Photography; Aperture (computer memory); Image restoration; Depth of field; Focus (optics); Digital photography; High-dynamic-range imaging; High dynamic range; Variable (mathematics); Noise (video); Computer graphics (images); Dynamic range; Image (mathematics); Image processing; Mathematics; Optics; Engineering","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":[0.0001390881,0.00007387347,0.00005789228,0.00006641608,0.00006819448,0.00003460513,0.00007736199,0.0001071693,0.00003352722],"category_scores_gemma":[0.00003179222,0.00006950252,0.00003372296,0.0002837167,0.00001090688,0.00005238629,0.000003438463,0.00009093115,0.000004053032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001733403,"about_ca_system_score_gemma":0.000009950194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004808657,"about_ca_topic_score_gemma":0.000003488967,"domain_scores_codex":[0.999603,0.000001521861,0.0001078905,0.00009040492,0.00005270725,0.0001444849],"domain_scores_gemma":[0.9996243,0.0001297054,0.00001398191,0.0001516388,0.00004757378,0.00003287693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006515109,0.0001762383,0.0003362704,0.0004841397,0.00004776189,0.000001502402,0.0001667298,0.004026179,0.3052683,0.5948547,0.06319331,0.03137978],"study_design_scores_gemma":[0.0002607957,0.0000512805,0.0001146549,0.00007897768,0.00002157237,0.000001443241,0.00003003165,0.2106836,0.2022869,0.09469201,0.4914138,0.0003649888],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003286584,0.00007427898,0.9914564,0.0001541125,0.00004290783,0.0002296149,0.000007087359,0.0010328,0.006674076],"genre_scores_gemma":[0.2971898,0.000002410026,0.7021402,0.0004586238,0.00005110619,0.00008016745,0.00001923988,0.00001793103,0.00004048781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5001627,"threshold_uncertainty_score":0.283423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01659965586185785,"score_gpt":0.2772332890237749,"score_spread":0.260633633161917,"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."}}