用属性学习解释图像失真类型与程度，实现高精度可解释的盲评估。
ExIQA: Explainable Image Quality Assessment Using Distortion Attributes
- 通过视觉语言模型分析失真属性而非直接识别失真名称
- 在多个数据集上达到当前最优的PLCC和SRCC指标
- 支持多失真共存，适合需要透明决策的图像质量场景
无参考图像质量评估（BIQA）旨在不依赖参考图像的情况下估算图像质量。本文从失真识别的角度出发，利用视觉语言模型（如CLIP）的丰富知识与泛化能力，预测图像中失真的类型与强度。我们提出一种基于属性学习的可解释失真识别方法：不直接提示模型失真名称，而是提示其失真属性或效果，并聚合这些信息推断失真强度。同时考虑单张图像中存在多种失真，提升方法可扩展性。为此，我们构建了一个包含10万张图像的数据集以支持高效训练。最终，将属性概率输入回归器，预测图像质量分数。实验表明，该方法不仅具备可解释性与透明性，在多个数据集上的PLCC与SRCC指标均达到当前最优水平；零样本测试也验证了其良好泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。