TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment

Benchmark Model Rank Results
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ trained on SPAQ (NR)#11SROCC: 0.64923PLCC: 0.60905KLCC: 0.53140Type: NR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ#14SROCC: 0.62715PLCC: 0.57674KLCC: 0.50670Type: NR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ FACE#20SROCC: 0.59564PLCC: 0.58949KLCC: 0.48428Type: NR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ#22SROCC: 0.57341PLCC: 0.57955KLCC: 0.46217Type: FR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ trained on PIPAL#26SROCC: 0.55568PLCC: 0.57564KLCC: 0.42811Type: FR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ (IAA)#33SROCC: 0.51687PLCC: 0.51061KLCC: 0.40663Type: NR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ + Res50 (IAA)#37SROCC: 0.36204PLCC: 0.34000KLCC: 0.28473Type: NR
video-quality-assessment-on-msu-sr-qa-datasetTOPIQ trained on FLIVE#38SROCC: 0.34092PLCC: 0.33940KLCC: 0.26774Type: NR