{"id":"W2293876531","doi":"10.1109/tip.2015.2436340","title":"High Dynamic Range Image Compression by Optimizing Tone Mapped Image Quality Index","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Tone mapping; High dynamic range; Computer science; Image quality; Naturalness; Artificial intelligence; Computer vision; Image (mathematics); Range (aeronautics); Metric (unit); Tone (literature); Image compression; Dynamic range; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009550749,0.0005124573,0.000513841,0.0003648498,0.0005738334,0.001054243,0.001230306,0.0001798486,0.00004971457],"category_scores_gemma":[0.00002810705,0.000516349,0.0001504804,0.0008568575,0.0002802416,0.004849008,0.00003162963,0.0007322218,0.0001059227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003945589,"about_ca_system_score_gemma":0.0002064496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001844878,"about_ca_topic_score_gemma":0.00001296384,"domain_scores_codex":[0.9962749,0.0002834561,0.000756585,0.001007792,0.0009364085,0.0007407995],"domain_scores_gemma":[0.9977534,0.0000975009,0.0003715585,0.0009536747,0.0005247071,0.0002991059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001641015,0.0007973945,0.000005070759,0.0002433111,0.00003448949,0.00005202278,0.001462698,0.0003668661,0.8312864,0.00001761017,0.003171035,0.162399],"study_design_scores_gemma":[0.002174094,0.0001725106,0.00004412454,0.0003466059,0.00003608622,0.00003295697,0.0002456557,0.1838933,0.8111475,0.0007829987,0.0002130793,0.0009111217],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004902945,0.0002230469,0.9899525,0.001017189,0.0004942259,0.0005400707,0.00003632381,0.001808598,0.001025085],"genre_scores_gemma":[0.5451344,0.00002506832,0.4539124,0.0002530839,0.00002730565,0.0001100421,0.000008870497,0.00004984553,0.0004790705],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5402314,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02238372510821498,"score_gpt":0.3246670638641913,"score_spread":0.3022833387559763,"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."}}