Blind Super-Resolution via Meta-Learning and Markov Chain Monte Carlo Simulation

Learning based approaches have witnessed great successes in blind single image super-resolution (SISR) tasks, however, handcrafted kernel priors and learning based kernel priors are typically required. In this paper, we propose a meta-learning and Markov Chain Monte Carlo (MCMC) based SISR approach to learn kernel priors from organized randomness. In concrete, a lightweight network is adopted as kernel generator, and is optimized via learning from the MCMC simulation on random Gaussian distributions. This procedure provides an approximation for the rational blur kernel, and introduces a network-level Langevin dynamics into SISR optimization processes, which contributes to preventing bad local optimal solutions for kernel estimation. Meanwhile, a meta-learning based alternating optimization procedure is proposed to optimize the kernel generator and image restorer, respectively. In contrast to the conventional alternating minimization strategy, a meta-learning based framework is applied to learn an adaptive optimization strategy, which is less-greedy and results in better convergence performance. These two procedures are iteratively processed in a plug-and-play fashion, for the first time, realizing a learning-based but plug-and-play blind SISR solution in unsupervised inference. Extensive simulations demonstrate the superior performance and generalization ability of the proposed approach when compared with the Start-of-the-Art solutions on synthesis and real-world datasets.

I. Introduction

Single image super-resolution (SISR) plays a crucial role in image processing society. It tends to reconstruct high-resolution (HR) images from the low-resolution (LR) observations. With the fact that the degradation model is typically unknown in real-world scenarios, growing studies begin to predict the blur kernels and the HR images simultaneously, known as the blind SISR problem. A common mechanism to solve the blind SISR problem is underlying an alternating optimization between two sub-problems, kernel estimation and image restoration, which are iteratively minimized until the HR image is restored. Kernel estimation is a pivotal step in solving blind SISR problems, which determines the HR image reconstruction performance, and thereby becomes the centrality study of this paper.