# JingyunLiang / FKP

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

https://arxiv.org/abs/2103.15977

Geek Repo

Github PK Tool

Here, lambda_1 and lambda_2 denote $\sigma_1^2$ and $\sigma_2^2$ in the covariance matrix, respectively. Therefore, it has already been squared. Note that isotropic Gaussian generation functions often take $\sigma$ (the standard deviation, not squared) as input.