{"id":"W2738579427","doi":"10.1109/cvpr.2017.33","title":"Deep Video Deblurring for Hand-Held Cameras","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":600,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology; University of British Columbia","funders":"King Abdullah University of Science and Technology","keywords":"Deblurring; Motion blur; Computer science; Artificial intelligence; Computer vision; Shake; Frame (networking); Task (project management); Frame rate; Deep learning; Motion (physics); Image (mathematics); Image restoration; Image processing","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":[],"consensus_categories":[],"category_scores_codex":[0.000149276,0.00009962328,0.000109518,0.0000415643,0.0007843389,0.0009074309,0.001585733,0.00003581432,0.00000559103],"category_scores_gemma":[0.0003158812,0.00008728808,0.00004332449,0.00003388834,0.00008612082,0.001519857,0.0004425451,0.00006435668,0.00001440817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002282035,"about_ca_system_score_gemma":0.00003071051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002834556,"about_ca_topic_score_gemma":0.00002461608,"domain_scores_codex":[0.9992175,0.000005576032,0.0001183723,0.0003121978,0.0001030635,0.0002433258],"domain_scores_gemma":[0.9987203,0.00005841913,0.0001108215,0.0009447609,0.0001090484,0.00005661569],"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":[0.00001016278,0.0000475468,0.001108698,0.00006261413,0.00001501243,0.0000116481,0.0004168295,0.00001849147,0.02871811,0.09817905,0.004043649,0.8673682],"study_design_scores_gemma":[0.0003669095,0.00007402256,0.0004456361,0.00005630778,0.000004900154,0.0000160277,0.0000079644,0.5516916,0.2623896,0.1655096,0.01909383,0.0003435927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001483471,0.00009774006,0.9924284,0.001369139,0.0001382758,0.0001413319,2.284344e-7,0.0004984043,0.005178127],"genre_scores_gemma":[0.1974363,0.0000046369,0.8012679,0.0004380978,0.00004675213,0.00004811654,2.046865e-7,0.000008991549,0.0007489826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8670246,"threshold_uncertainty_score":0.8750377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02547686489349839,"score_gpt":0.3245200094759543,"score_spread":0.299043144582456,"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."}}