This paper introduces a blind super-resolution technique, i.e. a method allowing to increase the resolution of an image without knowing the downscaling kernel. Clarity: clarity is fairly good. It's just that sometimes some statements are raising questions which are answered later in the paper. It would be better to warn the reader that explanations are coming next. The paper is technically sound.

The paper proposes a method for blind super-resolutions by estimating the kernel with a GAN. The method is based on zero-shot learning: it assumes unknown SR kernel, and thus estimates the kernel in a blind manner at test time. The method improves restoration quality by a large margin with the aid of the accurately estimated SR kernel. The paper is well written. Reviewers agreed since the beginning on the acceptance and are satisfied by the rebuttal.

Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed ideal' downscaling kernel (e.g. However, this is rarely the case in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gave rise to Blind-SR - namely, SR when the downscaling kernel (SR-kernel'') is unknown. It was further shown that the true SR-kernel is the one that maximizes the recurrence of patches across scales of the LR image.

Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed ideal' downscaling kernel (e.g. However, this is rarely the case in real LR images, in contrast to synthetically generated SR datasets. When the assumed downscaling kernel deviates from the true one, the performance of SR methods significantly deteriorates. This gave rise to Blind-SR - namely, SR when the downscaling kernel ( SR-kernel'') is unknown. It was further shown that the true SR-kernel is the one that maximizes the recurrence of patches across scales of the LR image.