One of the long-standing challenges in photography is noise. Noise artifacts are generated from relative motion between a camera and a scene during exposure. While noise can be reduced by using a shorter exposure, this comes at an unavoidable trade-off with increased noise. Therefore, it is desirable to remove noise computationally. To remove noise, we need to (i) estimate how the image is noised (i.e. the blur kernel or the point-spread function) and (ii) restore a natural looking image through deconvolution. Blur kernel estimation is challenging because the algorithm needs to distinguish...