{"id":"W4286239565","doi":"10.48550/arxiv.2207.08689","title":"Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fidelity; Weighting; Computer science; Image quality; Image (mathematics); Artificial intelligence; Quality (philosophy); Contrast (vision); Resolution (logic); Algorithm; Pattern recognition (psychology); Machine learning; Data mining; Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007697556,0.0002659835,0.0004630956,0.0001551434,0.0002228467,0.0001008225,0.001242473,0.0001198462,0.00005315736],"category_scores_gemma":[0.0002159652,0.0003289903,0.00008839668,0.0003034332,0.0003351325,0.0004492121,0.004541342,0.0006799419,0.000001199871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003599079,"about_ca_system_score_gemma":0.0004280458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000129973,"about_ca_topic_score_gemma":0.00001068679,"domain_scores_codex":[0.9976452,0.0003853019,0.0003905367,0.001093469,0.000189587,0.0002959332],"domain_scores_gemma":[0.9977416,0.0003868247,0.0003851448,0.001136185,0.000218275,0.0001320047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008036323,0.0005476068,0.0239026,0.002113851,0.000139005,0.00117058,0.0005847516,0.01604715,0.003226383,0.9440736,0.0004355323,0.007678645],"study_design_scores_gemma":[0.0002395505,0.00008120688,0.02233143,0.00006376902,0.00003570205,0.000008628649,0.00006325627,0.8030534,0.00006761108,0.1735742,0.00009725065,0.0003839935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03016818,0.00004916827,0.9678493,0.00004848267,0.000152097,0.0002157487,0.0001142045,0.0002904442,0.001112403],"genre_scores_gemma":[0.6488971,0.00004023609,0.3509321,0.00003085747,0.00001110181,0.000002094899,0.00001626026,0.000009103952,0.00006118159],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7870063,"threshold_uncertainty_score":0.9999162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08541980073831809,"score_gpt":0.2898153755233935,"score_spread":0.2043955747850754,"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."}}