The visual quality of an image is confounded by a number of intertwined
factors including its semantic content, distortion characteristics and
appearance properties such as brightness, contrast, sharpness, and
colourfulness. Distilling high level knowledge about all these quality bearing
attributes is crucial for developing objective Image Quality Assessment
(IQA).While existing solutions have modeled some of these aspects, a
comprehensive solution that involves all these important quality related
attributes has not yet been developed. In this paper, we present a new blind
IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image
QUality Evaluator (SLIQUE) that features a joint vision-language and visual
contrastive representation learning framework for acquiring high level
knowledge about the images semantic contents, distortion characteristics and
appearance properties for IQA. For training SLIQUE, we have developed a
systematic approach to constructing a first of its kind large image database
annotated with all three categories of quality relevant texts. The Text
Annotated Distortion, Appearance and Content (TADAC) database has over 1.6
million images annotated with textual descriptions of their semantic contents,
distortion characteristics and appearance properties. The method for
constructing TADAC and the database itself will be particularly useful for
exploiting vision-language modeling for advanced IQA applications. Extensive
experimental results show that SLIQUE has superior performances over state of
the art, demonstrating the soundness of its design principle and the
effectiveness of its implementation.

本文介绍了一种名为 SLIQUE 的新型盲目图像质量评估 (BIQA) 模型，该模型采用联合视觉 - 语言和视觉对比表示学习框架，通过获取关于图像语义内容、畸变特征和外观属性的高级知识来进行质量评估。为了训练 SLIQUE，我们开发了一种系统的方法来构建一个首个具有所有三类质量相关文本注释的大型图像数据库 TADAC。TADAC 数据库拥有超过 160 万张图像，用文本描述它们的语义内容、畸变特征和外观属性。构建 TADAC 的方法和数据库本身将特别有助于利用视觉 - 语言建模进行高级图像质量评估应用。大量实验结果显示，SLIQUE 在性能上优于现有技术，证明了其设计原理的完整性和实现的有效性。