Image Super-Resolution using Explicit Perceptual Loss

TL;DR

This paper introduces an explicit perceptual loss for image super-resolution that directly optimizes for perceptual quality, leading to more visually pleasing images and better interpretability compared to traditional methods.

Contribution

The paper presents a novel explicit perceptual loss function trained to directly optimize perceptual scores, improving interpretability and visual quality in super-resolution tasks.

Findings

Explicit perceptual loss outperforms traditional loss functions in perceptual scores.

The approach yields images that are more visually pleasing according to subjective evaluation.

The method enhances interpretability of the optimization process.

Abstract

This paper proposes an explicit way to optimize the super-resolution network for generating visually pleasing images. The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to improve the perceptual score. We show how to exploit the machine learning based model which is directly trained to provide the perceptual score on generated images. It is believed that these models can be used to optimizes the super-resolution network which is easier to interpret. We further analyze the characteristic of the existing loss and our proposed explicit perceptual loss for better interpretation. The experimental results show the explicit approach has a higher perceptual score than other approaches. Finally, we demonstrate the relation of explicit perceptual loss and visually pleasing images using subjective evaluation.