ISTA-Inspired Network for Image Super-Resolution

TL;DR

This paper introduces an interpretable image super-resolution network inspired by the ISTA optimization algorithm, combining multi-scale techniques to achieve competitive results with fewer parameters.

Contribution

It develops an ISTA-inspired network with multi-scale attention for interpretable and efficient image super-resolution, filling a gap in optimization-based deep learning methods.

Findings

Achieves competitive or superior performance compared to other optimization-inspired methods.

Uses fewer parameters and lower computational complexity.

Provides an interpretable framework based on mathematical optimization principles.

Abstract

Deep learning for image super-resolution (SR) has been investigated by numerous researchers in recent years. Most of the works concentrate on effective block designs and improve the network representation but lack interpretation. There are also iterative optimization-inspired networks for image SR, which take the solution step as a whole without giving an explicit optimization step. This paper proposes an unfolding iterative shrinkage thresholding algorithm (ISTA) inspired network for interpretable image SR. Specifically, we analyze the problem of image SR and propose a solution based on the ISTA method. Inspired by the mathematical analysis, the ISTA block is developed to conduct the optimization in an end-to-end manner. To make the exploration more effective, a multi-scale exploitation block and multi-scale attention mechanism are devised to build the ISTA block. Experimental results show the proposed ISTA-inspired restoration network (ISTAR) achieves competitive or better performances than other optimization-inspired works with fewer parameters and lower computation complexity.