IKC
IKC copied to clipboard
Implementation of 'Blind Super-Resolution With Iterative Kernel Correction' (CVPR2019)
When compare with other methods such as CARN, did you use your own degradation dataset to retrain the network?
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...
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,...
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...
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...
hello,Where did the pca_matrix.pth come from?which paper and which author? I want to generate one,thanks!