{"id":"W2519597608","doi":"10.1007/978-3-319-46487-9_45","title":"Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deblurring; Computer science; Deconvolution; Computer vision; Blind deconvolution; Artificial intelligence; Kernel (algebra); Scale (ratio); Motion blur; Image restoration; Computer graphics (images); Image (mathematics); Image processing; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009464217,0.0004825759,0.0005376593,0.001107406,0.0002576917,0.0002365859,0.002519052,0.0002496269,0.00001039817],"category_scores_gemma":[0.0002187322,0.0004030571,0.0001563138,0.0006342382,0.0008627942,0.0005391605,0.0009899852,0.0004589293,0.000005589706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018022,"about_ca_system_score_gemma":0.0004293969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007857554,"about_ca_topic_score_gemma":0.000006356869,"domain_scores_codex":[0.9964753,0.00003059391,0.0006316032,0.001440088,0.0007710261,0.0006513596],"domain_scores_gemma":[0.9969776,0.0005944155,0.0006507243,0.0009914042,0.0006702891,0.0001156131],"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":[0.00002844903,0.00003772004,0.0000158882,0.0001231558,0.00001718344,0.000007903204,0.0005745606,0.02878798,0.005364365,0.0193423,0.000009692772,0.9456908],"study_design_scores_gemma":[0.0009122101,0.0006506062,0.00001670399,0.001286107,0.00001581633,0.00002214127,2.960186e-7,0.4991383,0.04444839,0.451718,0.0009253582,0.0008660928],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008951389,0.0003526052,0.9969727,0.0002849816,0.0008414779,0.000729461,0.000005470418,0.000278613,0.0004452033],"genre_scores_gemma":[0.08668093,0.00004131914,0.9126462,0.0002146372,0.0001223149,0.00004352345,0.00000333269,0.00003597064,0.0002118087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9448247,"threshold_uncertainty_score":0.9998421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0112317123347765,"score_gpt":0.2663833764137624,"score_spread":0.2551516640789859,"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."}}