Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching

TL;DR

This paper introduces a memory-driven framework for image quality assessment that mimics human visual memory, enabling effective evaluation with or without reference images by matching distortion patterns stored in a memory bank.

Contribution

The proposed MQAF framework is the first to incorporate a memory bank of distortion patterns for adaptive quality assessment in both reference-based and no-reference scenarios.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effectively switches between reference-guided and no-reference modes.

Achieves high accuracy in real-world applications without high-quality references.

Abstract

Existing full-reference image quality assessment (FR-IQA) methods achieve high-precision evaluation by analysing feature differences between reference and distorted images. However, their performance is constrained by the quality of the reference image, which limits real-world applications where ideal reference sources are unavailable. Notably, the human visual system has the ability to accumulate visual memory, allowing image quality assessment on the basis of long-term memory storage. Inspired by this biological memory mechanism, we propose a memory-driven quality-aware framework (MQAF), which establishes a memory bank for storing distortion patterns and dynamically switches between dual-mode quality assessment strategies to reduce reliance on high-quality reference images. When reference images are available, MQAF obtains reference-guided quality scores by adaptively weighting reference information and comparing the distorted image with stored distortion patterns in the memory bank. When the reference image is absent, the framework relies on distortion patterns in the memory bank to infer image quality, enabling no-reference quality assessment (NR-IQA). The experimental results show that our method outperforms state-of-the-art approaches across multiple datasets while adapting to both no-reference and full-reference tasks.