MASA-SR icon indicating copy to clipboard operation
MASA-SR copied to clipboard

About PSNR/SSIM in Table 1

Open ximu1211 opened this issue 3 years ago • 2 comments

I have read a few RefSR papers recently. Why is everyone's comparative effect data the same over the years?

ximu1211 avatar Nov 16 '21 02:11 ximu1211

For the fair comparison. Actually, there are some recent papers that propose new datasets, for example: Dual-Camera Super-Resolution with Aligned Attention Modules.

SkyeLu avatar Nov 19 '21 09:11 SkyeLu

For the fair comparison. Actually, there are some recent papers that propose new datasets, for example: Dual-Camera Super-Resolution with Aligned Attention Modules.

I mean,why is everyone's PSNR/SSIM is same. Every year’s work is like taking the previous year’s results and adding the psnr/ssim from new own model. Instead of writing the results of running in our own environment

ximu1211 avatar Nov 19 '21 09:11 ximu1211