Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques

TL;DR

This paper introduces an adaptive loss function for super-resolution CNNs that leverages convex optimization to improve detail recovery and training stability, addressing limitations of GAN-based methods.

Contribution

It proposes a novel convex optimization-based space for CNN training, enhancing detail preservation and stability in super-resolution tasks.

Findings

Improved recovery of fine image details.

Enhanced training stability of CNNs.

Effective high-frequency component learning.

Abstract

Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional Neural Networks (CNNs) have achieved state of the art performance on SISR. However, the images produced by CNNs do not contain fine details of the images. Generative Adversarial Networks (GANs) aim to solve this issue and recover sharp details. Nevertheless, GANs are notoriously difficult to train. Besides that, they generate artifacts in the high-resolution images. In this paper, we have proposed a method in which CNNs try to align images in different spaces rather than only the pixel space. Such a space is designed using convex optimization techniques. CNNs are encouraged to learn high-frequency components of the images as well as low-frequency components. We have shown that the proposed method can recover fine details of the images and it is stable in the training process.