JingyunLiang / FKP

Official PyTorch code for Flow-based Kernel Prior with Application to Blind Super-Resolution (FKP, CVPR2021)

Home Page:https://arxiv.org/abs/2103.15977

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Pixel Offset Problem

jiandandan001 opened this issue · comments

Hi, thank you for sharing the code.

I have an LR image and corresponding HR image.

We use the LR image as the input to the KernelGAN-FKP, and obtain a super-resolved image without ground-truth kernels, .

It seems that there is pixel offset between the super-resolved image and the original HR image, leading to a very low PSNR of the super-resolved image.

Do you know how to solve this problem?

We assume the blur kernel is shifted in image degradation, so the generated SR image is shifted. For your case, one possible way is to shift the SR image (e.g. for 0.25, 0.5, 0.75, 1.0, 1.25 pixels) to find the best PSNR.

Feel free to open it if you have more questions.

ezoic increase your site revenue