Frequency Separation for Real-World Super-Resolution

TL;DR

This paper introduces a frequency separation approach combined with DSGAN to improve real-world image super-resolution, addressing the limitations of traditional methods that rely on idealized training data.

Contribution

It proposes a novel unsupervised training method using DSGAN to generate realistic LR images and separates image frequencies to enhance super-resolution performance in real-world scenarios.

Findings

Significant improvement on real-world SR benchmarks.

Winning the AIM Challenge on Real World SR at ICCV 2019.

Effective separation of low and high frequencies during training.

Abstract

Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in real-world settings. This is because real-world images can be subject to corruptions such as sensor noise, which are severely altered by bicubic downscaling. Therefore, the models never see a real-world image during training, which limits their generalization capabilities. Moreover, it is cumbersome to collect paired LR and HR images in the same source domain. To address this problem, we propose DSGAN to introduce natural image characteristics in bicubically downscaled images. It can be trained in an unsupervised fashion on HR images, thereby generating LR images with the same characteristics as the original images. We then use the generated data to train a SR model, which greatly improves its performance on real-world images. Furthermore, we propose to separate the low and high image frequencies and treat them differently during training. Since the low frequencies are preserved by downsampling operations, we only require adversarial training to modify the high frequencies. This idea is applied to our DSGAN model as well as the SR model. We demonstrate the effectiveness of our method in several experiments through quantitative and qualitative analysis. Our solution is the winner of the AIM Challenge on Real World SR at ICCV 2019.