You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
HI! thanks for the great job!
When I use different calculation metrics in pyiqa to evaluate the results,there is a performance gap between the PSNR and SSIM results and the results reported in paper. The results of other metrics are nearly identical to the results reported in paper .
I use center crop on RealSR image to get a 128×128 patch and calculate on the Y channel in YCbCrspace.
our results : PSNR :24.63 SSIM :0.7195
results on the paper : PSNR :25.15 SSIM:0.7341
May I ask what's wrong with my approach? Others,could you provide the code for the metric testing. Thanks!
The text was updated successfully, but these errors were encountered:
HI! thanks for the great job!
When I use different calculation metrics in pyiqa to evaluate the results,there is a performance gap between the PSNR and SSIM results and the results reported in paper. The results of other metrics are nearly identical to the results reported in paper .
I use center crop on RealSR image to get a 128×128 patch and calculate on the Y channel in YCbCrspace.
our results : PSNR :24.63 SSIM :0.7195
results on the paper : PSNR :25.15 SSIM:0.7341
May I ask what's wrong with my approach? Others,could you provide the code for the metric testing. Thanks!
The text was updated successfully, but these errors were encountered: