Nowadays, most existing blind image quality assessment (BIQA) models 1) are developed for synthetically-distorted images and often generalize poorly to authentic ones; 2) heavily rely on human ratings, which are prohibitively labor-expensive to collect. Here, we propose an $opinion$-$free$ BIQA method that learns from synthetically-distorted images and multiple agents to assess the perceptual quality of authentically-distorted ones captured in the wild without relying on human labels. Specifically, we first assemble a large number of image pairs from synthetically-distorted images and use a set of full-reference image quality assessment (FR-IQA) models to assign pseudo-binary labels of each pair indicating which image has higher quality as the supervisory signal. We then train a convolutional neural network (CNN)-based BIQA model to rank the perceptual quality, optimized for consistency with the binary labels. Since there exists domain shift between the synthetically- and authentically-distorted images, an unsupervised domain adaptation (UDA) module is introduced to alleviate this issue. Extensive experiments demonstrate the effectiveness of our proposed $opinion$-$free$ BIQA model, yielding state-of-the-art performance in terms of correlation with human opinion scores, as well as gMAD competition. Codes will be made publicly available upon acceptance.

中文翻译：

---

从合成数据中学习用于野外无意见盲图像质量评估

如今，大多数现有的盲图像质量评估 (BIQA) 模型 1) 都是为合成失真的图像而开发的，并且通常很难推广到真实的图像；2) 严重依赖人工评分，收集人工评分非常昂贵。在这里，我们提出了一种 $opinion$-$free$ BIQA 方法，该方法从合成失真的图像和多个代理中学习，以评估在野外捕获的真实失真图像的感知质量，而无需依赖人工标签。具体来说，我们首先从合成失真的图像中组装大量图像对，并使用一组全参考图像质量评估 (FR-IQA) 模型来分配每对的伪二进制标签，指示哪个图像具有更高的质量作为监控信号。然后，我们训练基于卷积神经网络 (CNN) 的 BIQA 模型对感知质量进行排名，并针对与二元标签的一致性进行了优化。由于合成失真图像和真实失真图像之间存在域偏移，因此引入了无监督域自适应 (UDA) 模块来缓解此问题。大量实验证明了我们提出的 $opinion$-$free$ BIQA 模型的有效性，在与人类意见分数的相关性以及 gMAD 竞争方面产生了最先进的性能。代码将在接受后公开提供。大量实验证明了我们提出的 $opinion$-$free$ BIQA 模型的有效性，在与人类意见分数的相关性以及 gMAD 竞争方面产生了最先进的性能。代码将在接受后公开提供。大量实验证明了我们提出的 $opinion$-$free$ BIQA 模型的有效性，在与人类意见分数的相关性以及 gMAD 竞争方面产生了最先进的性能。代码将在接受后公开提供。