How Real is Real: Evaluating the Robustness of Real-World Super Resolution

TL;DR

This paper evaluates the robustness of current super-resolution methods on real-world images, introduces a new dataset WideRealSR, and proposes solutions to improve generalization in practical applications.

Contribution

The paper provides a comprehensive evaluation of super-resolution methods on real images, introduces the WideRealSR dataset, and suggests approaches to enhance model generalization.

Findings

State-of-the-art methods vary in performance on real-world images.

WideRealSR dataset captures diverse real-life scenarios.

Proposed solutions improve generalization in super-resolution models.

Abstract

Image super-resolution (SR) is a field in computer vision that focuses on reconstructing high-resolution images from the respective low-resolution image. However, super-resolution is a well-known ill-posed problem as most methods rely on the downsampling method performed on the high-resolution image to form the low-resolution image to be known. Unfortunately, this is not something that is available in real-life super-resolution applications such as increasing the quality of a photo taken on a mobile phone. In this paper we will evaluate multiple state-of-the-art super-resolution methods and gauge their performance when presented with various types of real-life images and discuss the benefits and drawbacks of each method. We also introduce a novel dataset, WideRealSR, containing real images from a wide variety of sources. Finally, through careful experimentation and evaluation, we will present a potential solution to alleviate the generalization problem which is imminent in most state-of-the-art super-resolution models.