Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN

TL;DR

This paper introduces Dual Perceptual Loss (DP Loss) for single image super-resolution, combining VGG and ResNet features to enhance reconstruction quality and address issues of distortion and oversmoothing.

Contribution

The paper proposes a novel Dual Perceptual Loss that leverages complementary features from VGG and ResNet to improve super-resolution results over existing methods.

Findings

DP Loss significantly improves image reconstruction quality.

The method outperforms state-of-the-art super-resolution techniques.

Qualitative and quantitative results validate the effectiveness.

Abstract

The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction. Furthermore, the generative adversarial networks (GAN) is applied to the super-resolution field, which effectively improves the visual quality of the reconstructed image. However, under the condtion of high upscaling factors, the excessive abnormal reasoning of the network produces some distorted structures, so that there is a certain deviation between the reconstructed image and the ground-truth image. In order to fundamentally improve the quality of reconstructed images, this paper proposes a effective method called Dual Perceptual Loss (DP Loss), which is used to replace the original perceptual loss to solve the problem of single image super-resolution reconstruction. Due to the complementary property between the VGG features and the ResNet features, the proposed DP Loss considers the advantages of learning two features simultaneously, which significantly improves the reconstruction effect of images. The qualitative and quantitative analysis on benchmark datasets demonstrates the superiority of our proposed method over state-of-the-art super-resolution methods.