SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

TL;DR

SRPGAN introduces a perceptual GAN framework for single image super resolution that effectively reconstructs high-frequency details and sharp edges, outperforming previous CNN-based methods in SSIM scores.

Contribution

The paper proposes a novel perceptual loss based on the discriminator in a GAN framework, improving detail recovery in super resolution tasks.

Findings

Achieves higher SSIM scores than previous methods on multiple benchmarks.

Produces images with sharper edges and richer details.

Demonstrates robustness across different scaling factors.

Abstract

Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural network (CNN) based models have achieved great performance on SISR task. Despite the breakthroughs achieved by using CNN models, there are still some problems remaining unsolved, such as how to recover high frequency details of high resolution images. Previous CNN based models always use a pixel wise loss, such as l2 loss. Although the high resolution images constructed by these models have high peak signal-to-noise ratio (PSNR), they often tend to be blurry and lack high-frequency details, especially at a large scaling factor. In this paper, we build a super resolution perceptual generative adversarial network (SRPGAN) framework for SISR tasks. In the framework, we propose a robust perceptual loss based on the discriminator of the built SRPGAN model. We use the Charbonnier loss function to build the content loss and combine it with the proposed perceptual loss and the adversarial loss. Compared with other state-of-the-art methods, our method has demonstrated great ability to construct images with sharp edges and rich details. We also evaluate our method on different benchmarks and compare it with previous CNN based methods. The results show that our method can achieve much higher structural similarity index (SSIM) scores on most of the benchmarks than the previous state-of-art methods.