KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment

Blind super-resolution (SR) methods aim to generate a high quality high resolution image from a low resolution image containing unknown degradations. However, natural images contain various types and amounts of blur: some may be due to the inherent degradation characteristics of the camera, but some may even be intentional, for aesthetic purposes (e.g. Bokeh effect). In the case of the latter, it becomes highly difficult for SR methods to disentangle the blur to remove, and that to leave as is. In this paper, we propose a novel blind SR framework based on kernel-oriented adaptive local adjustment (KOALA) of SR features, called KOALAnet, which jointly learns spatially-variant degradation and restoration kernels in order to adapt to the spatially-variant blur characteristics in real images. Our KOALAnet outperforms recent blind SR methods for synthesized LR images obtained with randomized degradations, and we further show that the proposed KOALAnet produces the most natural results for artistic photographs with intentional blur, which are not over-sharpened, by effectively handling images mixed with in-focus and out-of-focus areas.

1. Introduction

When a deep neural network is trained under a specific scenario, its generalization ability tends to be limited to that particular setting, and its performance deteriorates under a different condition. This is a major problem in single image super-resolution (SR), where most neural-network-based methods have focused on the upscaling of low resolution (LR) images to high resolution (HR) images solely under the bicubic downsampling setting [13], [15], [16], [26], until very recently. Naturally, their performance tends to severely drop if the input LR image is degraded by even a slightly different downsampling kernel, which is often the case in real images [23]. Hence, more recent SR methods aim for blind SR, where the true degradation kernels are unknown [5], [8].