Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network

TL;DR

This paper introduces MoG-DUN, an explainable, efficient deep unfolding network for image super-resolution that integrates model-based priors with deep learning, outperforming existing methods in accuracy and versatility.

Contribution

The paper proposes a novel model-guided deep unfolding network that combines nonlocal auto-regressive priors with deep denoising modules for transparent and efficient super-resolution.

Findings

MoG-DUN achieves higher visual quality with fewer artifacts.

It is computationally efficient with reduced model parameters.

The method handles multiple degradation scenarios effectively.

Abstract

Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR). However, existing state-of-the-art SISR techniques are designed like black boxes lacking transparency and interpretability. Moreover, the improvement in visual quality is often at the price of increased model complexity due to black-box design. In this paper, we present and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN). Targeting at breaking the coherence barrier, we opt to work with a well-established image prior named nonlocal auto-regressive model and use it to guide our DNN design. By integrating deep denoising and nonlocal regularization as trainable modules within a deep learning framework, we can unfold the iterative process of model-based SISR into a multi-stage concatenation of building blocks with three interconnected modules (denoising, nonlocal-AR, and reconstruction). The design of all three modules leverages the latest advances including dense/skip connections as well as fast nonlocal implementation. In addition to explainability, MoG-DUN is accurate (producing fewer aliasing artifacts), computationally efficient (with reduced model parameters), and versatile (capable of handling multiple degradations). The superiority of the proposed MoG-DUN method to existing state-of-the-art image SR methods including RCAN, SRMDNF, and SRFBN is substantiated by extensive experiments on several popular datasets and various degradation scenarios.