Seven ways to improve example-based single image super resolution

TL;DR

This paper introduces seven practical techniques to enhance example-based single image super resolution, leading to significant improvements across standard benchmarks and setting new state-of-the-art results with minimal complexity increase.

Contribution

The paper presents seven widely applicable techniques that improve existing SR methods without major modifications, achieving new state-of-the-art performance.

Findings

Achieved up to 0.9dB PSNR improvement on benchmarks.

Validated techniques on multiple SR methods and datasets.

Enhanced SR performance with minimal computational overhead.

Abstract

In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, 5) back projection refinement, 6) enhanced prediction by consistency check, and 7) context reasoning. We validate our seven techniques on standard SR benchmarks (i.e. Set5, Set14, B100) and methods (i.e. A+, SRCNN, ANR, Zeyde, Yang) and achieve substantial improvements.The techniques are widely applicable and require no changes or only minor adjustments of the SR methods. Moreover, our Improved A+ (IA) method sets new state-of-the-art results outperforming A+ by up to 0.9dB on average PSNR whilst maintaining a low time complexity.