Has anyone tested the effect on other datasets?

[maclory]

Has anyone tested the effect on other datasets?

[MARIOXIAN]

I got the same problem when I downsampled CelebA dataset to 16x16. That is weird. However, the authors created the LR by downsampling HR images just with bicubic degradation in their paper.

我看了您的资料介绍，我就说中文吧，英文不太好。我观察了作者给的测试集，是用的png格式的CelebA中的人脸图像来测试的，在png格式下，把图像下采样后，超分的测试结果是很不错的。所以我把LFW的数据也转成png格式的了，结果伪影减少了，各项指标也很不错，具体是什么原因还不知道，希望能帮到你。

[kabutohui]

I got the same problem when I downsampled CelebA dataset to 16x16. That is weird. However, the authors created the LR by downsampling HR images just with bicubic degradation in their paper.

[Steve-Tod]

Hi there, please use png images. We found jpg compression leads to information loss in low res images, where any bit of image is very important.

[MARIOXIAN]

Has anybody done any experiments on face recognition rates?

[kabutohui]

Thanks, @MARIOXIAN , @Steve-Tod . Here's another tips, when you create LR png files from HR images, please use Image instead of OpenCV.