Single Image Super-Resolution

TL;DR

This paper reviews the evolution of single image super-resolution techniques, highlighting recent deep learning architectures that outperform earlier reconstruction-based methods in producing higher quality images.

Contribution

It provides a comprehensive chronological overview of super-resolution methods, emphasizing the advancements brought by deep learning architectures over traditional approaches.

Findings

Deep learning architectures outperform reconstruction-based methods

Latest network achieves higher quality super-resolution results

Quantitative results demonstrate significant improvements

Abstract

This study presents a chronological overview of the single image super-resolution problem. We first define the problem thoroughly and mention some of the serious challenges. Then the problem formulation and the performance metrics are defined. We give an overview of the previous methods relying on reconstruction based solutions and then continue with the deep learning approaches. We pick 3 landmark architectures and present their results quantitatively. We see that the latest proposed network gives favorable output compared to the previous methods.