Blind Image Quality Assessment (BIQA) is essential for automatically
evaluating the perceptual quality of visual signals without access to the
references. In this survey, we provide a comprehensive analysis and discussion
of recent developments in the field of BIQA. We have covered various aspects,
including hand-crafted BIQAs that focus on distortion-specific and
general-purpose methods, as well as deep-learned BIQAs that employ supervised
and unsupervised learning techniques. Additionally, we have explored multimodal
quality assessment methods that consider interactions between visual and audio
modalities, as well as visual and text modalities. Finally, we have offered
insights into representative BIQA databases, including both synthetic and
authentic distortions. We believe this survey provides valuable understandings
into the latest developments and emerging trends for the visual quality
community.

本综述对盲图像质量评估 (BIQA) 领域的最新发展和新兴趋势进行了全面分析和讨论，包括专注于特定畸变和通用方法的手工制作 BIQA、采用监督和无监督学习技术的深度学习 BIQA，以及考虑视觉与音频、视觉与文本模态之间相互作用的多模态质量评估方法。同时，还探讨了代表性的 BIQA 数据库，包括合成和真实畸变。我们相信，本综述对视觉质量社区的最新进展和新兴趋势提供了有价值的理解。

盲图像质量评估：简要调查

Blind Image Quality Assessment: A Brief Survey

Although many effective models and real-world datasets have been presented
for blind image quality assessment (BIQA), recent BIQA models usually tend to
fit specific training set. Hence, it is still difficult to accurately and
robustly measure the visual quality of an arbitrary real-world image. In this
paper, a robust BIQA method, is designed based on three aspects, i.e., robust
training strategy, large-scale real-world dataset, and powerful backbone.
First, many individual models based on popular and state-of-the-art (SOTA)
Swin-Transformer (SwinT) are trained on different real-world BIQA datasets
respectively. Then, these biased SwinT-based models are jointly used to
generate pseudo-labels, which adopts the probability of relative quality of two
random images instead of fixed quality score. A large-scale real-world image
dataset with 1,000,000 image pairs and pseudo-labels is then proposed for
training the final cross-dataset-robust model. Experimental results on
cross-dataset tests show that the performance of the proposed method is even
better than some SOTA methods that are directly trained on these datasets, thus
verifying the robustness and generalization of our method.

基于强健的训练策略、大规模真实世界数据集和强大的骨干网络，本研究设计了一个强健的盲图像质量评估方法，通过基于不同真实世界 BIQA 数据集训练多个基于 Swin-Transformer 的模型，并联合使用这些有偏差的模型生成伪标签，使用两个随机图像的相对质量概率而非固定质量分数，进而构建 1,000,000 个图像对和伪标签的大规模真实世界图像数据集，训练了最终的跨数据集强健模型。交叉数据集测试结果表明，所提出的方法的性能甚至优于直接在这些数据集上训练的一些最新方法，从而验证了该方法的强健性和泛化性。