Image restoration quality assessment based on regional differential information entropy
This addresses the issue for researchers and practitioners in image restoration where traditional metrics fail to align with perceived quality, though it is incremental as it builds on existing entropy-based methods.
The paper tackled the problem of subjective-objective inconsistency in image quality assessment for restored images by proposing a regional differential information entropy (RDIE) method, which achieved high agreement with human opinion scores on datasets like PIPAL.
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.