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

2025-01-24

AI Summary

Addressing the lack of reliable no-reference image quality assessment (IQA) methods in blind image restoration (BIR), this paper proposes a novel fidelity evaluation paradigm centered on degradation image consistency (CDI). We systematically reveal, for the first time, how solution non-uniqueness and degradation uncertainty in BIR negatively impact traditional image quality metrics (IQMs). To address this, we design a dual-path CDI framework: one path leverages wavelet-domain reference guidance, while the other operates in a fully reference-free manner. Furthermore, we introduce DISDCD—the first human-annotated dataset specifically designed for subjective fidelity evaluation in BIR. On DISDCD, CDI substantially outperforms full-reference metrics including PSNR, LPIPS, and DISTS, achieving strong alignment with human perception (SROCC > 0.89). Both the code and the DISDCD dataset will be publicly released.

Technology Category

• Computer Vision: Image and Video Retrieval
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• Generative Adversarial Networks
• Diffusion Models
• Blind Image Restoration

Innovation

• Blind Image Restoration
• Generative Adversarial Networks
• Diffusion Models Evaluation