Blind image quality assessment (IQA) in the wild, which assesses the quality of images with complex authentic distortions and no reference images, presents significant challenges. Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem. Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA (DP-IQA), to utilize the T2I model's prior for improved performance and generalization ability. Specifically, we utilize pre-trained Stable Diffusion as the backbone, extracting multi-level features from the denoising U-Net guided by prompt embeddings through a tunable text adapter. Simultaneously, an image adapter compensates for information loss introduced by the lossy pre-trained encoder. Unlike T2I models that require full image distribution modeling, our approach targets image quality assessment, which inherently requires fewer parameters. To improve applicability, we distill the knowledge into a lightweight CNN-based student model, significantly reducing parameters while maintaining or even enhancing generalization performance. Experimental results demonstrate that DP-IQA achieves state-of-the-art performance on various in-the-wild datasets, highlighting the superior generalization capability of T2I priors in blind IQA tasks. To our knowledge, DP-IQA is the first method to apply pre-trained diffusion priors in blind IQA. Codes and checkpoints are available at https://github.com/RomGai/DP-IQA.

翻译：真实场景下的盲图像质量评估（IQA）旨在评估具有复杂真实失真且无参考图像的图像质量，这带来了重大挑战。鉴于收集大规模训练数据的困难，如何利用有限数据开发出具有强泛化能力的模型仍是一个开放性问题。受预训练文生图（T2I）扩散模型强大图像感知能力的启发，我们提出了一种新颖的IQA方法——基于扩散先验的IQA（DP-IQA），以利用T2I模型的先验知识来提升性能和泛化能力。具体而言，我们以预训练的Stable Diffusion为骨干网络，通过一个可调文本适配器引导的提示嵌入，从去噪U-Net中提取多层次特征。同时，一个图像适配器用于补偿有损预训练编码器引入的信息损失。与需要完整图像分布建模的T2I模型不同，我们的方法针对图像质量评估任务，其本质所需参数量更少。为提高适用性，我们将知识蒸馏到一个轻量级的基于CNN的学生模型中，在显著减少参数量的同时，保持甚至提升了泛化性能。实验结果表明，DP-IQA在多个真实场景数据集上取得了最先进的性能，凸显了T2I先验在盲IQA任务中的卓越泛化能力。据我们所知，DP-IQA是首个将预训练扩散先验应用于盲IQA的方法。代码与模型检查点可在 https://github.com/RomGai/DP-IQA 获取。