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

TL;DR

This paper introduces a novel blind super-resolution method combining meta-learning and MCMC to learn kernel priors, improving convergence and generalization in unsupervised image restoration tasks.

Contribution

It proposes a meta-learning framework with MCMC simulation for kernel prior learning, enabling plug-and-play blind super-resolution without supervised training.

Findings

Outperforms state-of-the-art methods on synthesis datasets

Demonstrates strong generalization to real-world images

Achieves better convergence and stability in kernel estimation

Abstract

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 comparing with state-of-the-arts on synthesis and real-world datasets. The code is available at https://github.com/XYLGroup/MLMC.