Deep Model-Based Super-Resolution with Non-uniform Blur

TL;DR

This paper introduces a deep learning-based super-resolution method capable of handling spatially-varying blur, outperforming traditional uniform-blur assumptions and generalizing across various kernels and noise levels.

Contribution

It develops a fast deep plug-and-play algorithm for non-uniform blur super-resolution and unrolls it into an end-to-end trainable network, addressing a more realistic problem setting.

Findings

Achieves state-of-the-art performance on non-uniform blur super-resolution tasks.

Generalizes well to different blur kernels, noise levels, and scale factors.

Outperforms existing methods assuming uniform blur.

Abstract

We propose a state-of-the-art method for super-resolution with non-uniform blur. Single-image super-resolution methods seek to restore a high-resolution image from blurred, subsampled, and noisy measurements. Despite their impressive performance, existing techniques usually assume a uniform blur kernel. Hence, these techniques do not generalize well to the more general case of non-uniform blur. Instead, in this paper, we address the more realistic and computationally challenging case of spatially-varying blur. To this end, we first propose a fast deep plug-and-play algorithm, based on linearized ADMM splitting techniques, which can solve the super-resolution problem with spatially-varying blur. Second, we unfold our iterative algorithm into a single network and train it end-to-end. In this way, we overcome the intricacy of manually tuning the parameters involved in the optimization scheme. Our algorithm presents remarkable performance and generalizes well after a single training to a large family of spatially-varying blur kernels, noise levels and scale factors.