Blind Image Super-Resolution with Spatial Context Hallucination

TL;DR

This paper introduces a Spatial Context Hallucination Network (SCHN) that performs blind image super-resolution by jointly handling denoising, deblurring, and super-resolution, effectively managing unknown degradations.

Contribution

The novel SCHN framework integrates multiple restoration tasks into one model, improving performance on images with unknown blur and noise compared to existing methods.

Findings

Outperforms state-of-the-art methods on corrupted images

Effective handling of unknown blur kernels

Trained on high-quality datasets DIV2K and Flickr2K

Abstract

Deep convolution neural networks (CNNs) play a critical role in single image super-resolution (SISR) since the amazing improvement of high performance computing. However, most of the super-resolution (SR) methods only focus on recovering bicubic degradation. Reconstructing high-resolution (HR) images from randomly blurred and noisy low-resolution (LR) images is still a challenging problem. In this paper, we propose a novel Spatial Context Hallucination Network (SCHN) for blind super-resolution without knowing the degradation kernel. We find that when the blur kernel is unknown, separate deblurring and super-resolution could limit the performance because of the accumulation of error. Thus, we integrate denoising, deblurring and super-resolution within one framework to avoid such a problem. We train our model on two high quality datasets, DIV2K and Flickr2K. Our method performs better than state-of-the-art methods when input images are corrupted with random blur and noise.