CDI: Blind Image Restoration Fidelity Evaluation based on Consistency with Degraded Image

TL;DR

This paper introduces a novel no-reference image quality assessment method called CDI, which evaluates the fidelity of blind image restoration by measuring consistency with degraded images across various degradation types, outperforming existing IQA methods.

Contribution

The paper proposes a new CDI-based IQA system that assesses BIR fidelity without reference images and handles multiple degradation types, addressing limitations of existing methods.

Findings

CDI outperforms traditional Full Reference IQA methods in BIR fidelity evaluation.

The wavelet domain Reference Guided CDI effectively measures consistency across various degradations.

The proposed CDI system is validated on a new dataset, DISDCD, demonstrating superior performance.

Abstract

Recent advancements in Blind Image Restoration (BIR) methods, based on Generative Adversarial Networks and Diffusion Models, have significantly improved visual quality. However, they present significant challenges for Image Quality Assessment (IQA), as the existing Full-Reference IQA methods often rate images with high perceptual quality poorly. In this paper, we reassess the Solution Non-Uniqueness and Degradation Indeterminacy issues of BIR, and propose constructing a specific BIR IQA system. In stead of directly comparing a restored image with a reference image, the BIR IQA evaluates fidelity by calculating the Consistency with Degraded Image (CDI). Specifically, we propose a wavelet domain Reference Guided CDI algorithm, which can acquire the consistency with a degraded image for various types without requiring knowledge of degradation parameters. The supported degradation types include down sampling, blur, noise, JPEG and complex combined degradations etc. In addition, we propose a Reference Agnostic CDI, enabling BIR fidelity evaluation without reference images. Finally, in order to validate the rationality of CDI, we create a new Degraded Images Switch Display Comparison Dataset (DISDCD) for subjective evaluation of BIR fidelity. Experiments conducted on DISDCD verify that CDI is markedly superior to common Full Reference IQA methods for BIR fidelity evaluation. The source code and the DISDCD dataset will be publicly available shortly.