Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss

TL;DR

This paper introduces a modified U-net architecture combined with a mixed gradient loss function for single image super-resolution, improving edge reconstruction and reducing computational complexity.

Contribution

It proposes a novel loss function and a simplified U-net model that enhances super-resolution quality and efficiency compared to existing methods.

Findings

Better edge preservation in reconstructed images

Faster reconstruction with fewer parameters

High performance on multiple datasets

Abstract

Single image super-resolution (SISR) is the task of inferring a high-resolution image from a single low-resolution image. Recent research on super-resolution has achieved great progress due to the development of deep convolutional neural networks in the field of computer vision. Existing super-resolution reconstruction methods have high performances in the criterion of Mean Square Error (MSE) but most methods fail to reconstruct an image with shape edges. To solve this problem, the mixed gradient error, which is composed by MSE and a weighted mean gradient error, is proposed in this work and applied to a modified U-net network as the loss function. The modified U-net removes all batch normalization layers and one of the convolution layers in each block. The operation reduces the number of parameters, and therefore accelerates the reconstruction. Compared with the existing image super-resolution algorithms, the proposed reconstruction method has better performance and time consumption. The experiments demonstrate that modified U-net network architecture with mixed gradient loss yields high-level results on three image datasets: SET14, BSD300, ICDAR2003. Code is available online.