Has anyone tested the effect on other datasets?
MARIOXIAN opened this issue · comments
Has anybody done any experiments on face recognition rates?
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.
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。
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.
Thanks, @MARIOXIAN , @Steve-Tod . Here's another tips, when you create LR png files from HR images, please use Image
instead of OpenCV
.