Image restoration quality assessment based on regional differential information entropy

TL;DR

This paper introduces the RDIE method for image quality assessment, effectively evaluating images with similar textures but slight differences, aligning well with human perception and outperforming existing metrics.

Contribution

The paper proposes a novel regional differential information entropy approach that improves assessment accuracy and efficiency for images with subtle textural differences.

Findings

RDIE achieves higher correlation with human scores.

The method improves assessment speed and accuracy.

Experimental results outperform existing metrics.

Abstract

With the development of image recovery models,especially those based on adversarial and perceptual losses,the detailed texture portions of images are being recovered more naturally.However,these restored images are similar but not identical in detail texture to their reference images.With traditional image quality assessment methods,results with better subjective perceived quality often score lower in objective scoring.Assessment methods suffer from subjective and objective inconsistencies.This paper proposes a regional differential information entropy (RDIE) method for image quality assessment to address this problem.This approach allows better assessment of similar but not identical textural details and achieves good agreement with perceived quality.Neural networks are used to reshape the process of calculating information entropy,improving the speed and efficiency of the operation. Experiments conducted with this study image quality assessment dataset and the PIPAL dataset show that the proposed RDIE method yields a high degree of agreement with people average opinion scores compared to other image quality assessment metrics,proving that RDIE can better quantify the perceived quality of images.