{"id":"W4304084118","doi":"10.1145/3503161.3547899","title":"Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 30th ACM International Conference on Multimedia","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fidelity; Weighting; Computer science; Image quality; Image (mathematics); Artificial intelligence; Image resolution; Quality (philosophy); Resolution (logic); Contrast (vision); Algorithm; Pattern recognition (psychology); Machine learning; Computer vision; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005139355,0.0008738551,0.0009276669,0.00125799,0.0003041139,0.001941443,0.001102901,0.001234336,0.0008281683],"category_scores_gemma":[0.01830924,0.0004424264,0.0006698336,0.0007276096,0.001207026,0.002402443,0.00189797,0.001841005,0.0003099322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008392932,"about_ca_system_score_gemma":0.0006532653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002086995,"about_ca_topic_score_gemma":0.002196227,"domain_scores_codex":[0.9980253,0.0006621774,0.0001102963,0.0003682949,0.0007282226,0.0001057465],"domain_scores_gemma":[0.9930224,0.003797649,0.0009905455,0.0008754081,0.00109285,0.0002211363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005483463,0.0001091533,0.007243499,0.0006188834,0.000340722,0.0003187742,0.0003625057,0.5826386,0.05941219,0.01937626,0.002861303,0.3261698],"study_design_scores_gemma":[0.00001946724,0.0001216732,0.002868575,0.00006252867,0.00005351744,0.0003662045,0.0000540079,0.9614262,0.02129346,0.01213265,0.001558194,0.00004355981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03531318,0.001469441,0.9607018,0.0005069956,0.00005106288,0.00006517975,0.0001242809,0.0005155954,0.001252434],"genre_scores_gemma":[0.6515039,0.001908221,0.343692,0.0003968026,0.0001642481,0.00009885991,0.000412893,0.0003209396,0.00150212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005139355,"threshold_uncertainty_score":0.02717984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0551760696404402,"score_gpt":0.3771203647401609,"score_spread":0.3219442950997207,"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."}}