ExIQA: Explainable Image Quality Assessment Using Distortion Attributes

TL;DR

This paper introduces ExIQA, an explainable BIQA method that predicts distortion attributes using Vision-Language Models, enabling accurate and transparent image quality assessment without reference images.

Contribution

The paper proposes a novel attribute-based distortion identification approach using VLMs, generating a large dataset, and achieving state-of-the-art performance in blind image quality assessment.

Findings

Achieves state-of-the-art results on multiple datasets.

Demonstrates strong zero-shot generalization.

Provides explainability through attribute-based distortion inference.

Abstract

Blind Image Quality Assessment (BIQA) aims to develop methods that estimate the quality scores of images in the absence of a reference image. In this paper, we approach BIQA from a distortion identification perspective, where our primary goal is to predict distortion types and strengths using Vision-Language Models (VLMs), such as CLIP, due to their extensive knowledge and generalizability. Based on these predicted distortions, we then estimate the quality score of the image. To achieve this, we propose an explainable approach for distortion identification based on attribute learning. Instead of prompting VLMs with the names of distortions, we prompt them with the attributes or effects of distortions and aggregate this information to infer the distortion strength. Additionally, we consider multiple distortions per image, making our method more scalable. To support this, we generate a dataset consisting of 100,000 images for efficient training. Finally, attribute probabilities are retrieved and fed into a regressor to predict the image quality score. The results show that our approach, besides its explainability and transparency, achieves state-of-the-art (SOTA) performance across multiple datasets in both PLCC and SRCC metrics. Moreover, the zero-shot results demonstrate the generalizability of the proposed approach.