In this paper, we tackle no-reference image quality assessment (NR-IQA), which aims to predict the perceptual quality of a distorted image without referencing its pristine-quality counterpart. Inspired by the free-energy principle, we assume that, while perceiving a distorted image, the human visual system (HVS) tends to predict the pristine image then estimates the perceptual quality based on the distorted-restored pair. Furthermore, the perceptual quality depends heavily on the way how human beings attend to distorted images, namely, the cooperation of foveal vision and the eye movement mechanism. Inspired by these properties of the HVS, given the distorted-restored pair, we implement an attention-driven NR-IQA method with reinforcement learning (RL). The model learns a policy to attend to several regions parallelly. The observations of the fixation regions are aggregated in a weighted average way, which is inspired by the robust averaging strategy. For policy learning, the rewards are derived from two tasks—classifying the distortion type and estimating the perceptual score. The goal of policy learning is to maximize the expectation of the accumulated rewards. Extensive experiments on LIVE, TID2008, TID2013 and CSIQ demonstrate the superiority of our methods.

中文翻译：

---

无参考图像质量评估：注意力驱动的方法。


在本文中，我们解决无参考图像质量评估（NR-IQA），其目的是在不参考其原始质量对应物的情况下预测失真图像的感知质量。受自由能原理的启发，我们假设，在感知扭曲图像时，人类视觉系统（HVS）倾向于预测原始图像，然后根据扭曲恢复对估计感知质量。此外，感知质量在很大程度上取决于人类如何关注扭曲图像，即中央凹视觉和眼球运动机制的配合。受 HVS 这些特性的启发，给定扭曲恢复对，我们通过强化学习 (RL) 实现了注意力驱动的 NR-IQA 方法。该模型学习并行关注多个区域的策略。受稳健平均策略的启发，注视区域的观察结果以加权平均方式聚合。对于政策学习，奖励来自两个任务——对扭曲类型进行分类和估计感知得分。政策学习的目标是最大化累积奖励的期望。在 LIVE、TID2008、TID2013 和 CSIQ 上进行的大量实验证明了我们方法的优越性。