IKC

IKC copied to clipboard

About the comparation experiments

1

When compare with other methods such as CARN, did you use your own degradation dataset to retrain the network?

yiyunchen

How to train my own data

1

Hi. I want to train my own data. But the LR in my dataset is not aligned with the HR image pixels，when I use this network training, do I need...

InstantWindy

More accurate kernel estimation, but worse SR result

1

Hi, when I train IKC with a pertained SFTMD, the loss of kernel maps will get smaller and smaller, which indicates that the estimation of kernel is getting more accurate,...

greatlog

Detail of anisotropic gaussian kernel

1

In the generation of anisotropic gaussian kernel, see https://github.com/yuanjunchai/IKC/blob/b1103bda95363bb6c14ef8fc53e48d51dd0cbb9d/codes/utils/util.py#L244 why y is set as `y = np.clip(np.random.random() * scaling * x, sig_min, sig_max)`? Why don't choose the same way as...

JingyunLiang

Testing for scale 2

2

Hi, Thanks for providing the code! I tried testing for scale 2 by modifying the scale parameter in test_Predictor.yml and test_Corrector.yml, but the network keeps on upscaling the image by...

sooyekim

hello,Where did the pca_matrix.pth come from?which paper and which author? I want to generate one,thanks!

BugMaker-99