A survey on IQA

TL;DR

This survey reviews various image and video quality assessment methods, emphasizing recent deep learning-based non-reference approaches that outperform traditional models, and discusses datasets and future challenges.

Contribution

It provides a comprehensive overview of IQA and VQA concepts, metrics, and recent deep learning-based non-reference methods, highlighting their advancements and challenges.

Findings

Deep learning-based NR-IQA methods outperform traditional models.

Synthetic and real-world databases are crucial for evaluating IQA methods.

The survey identifies key challenges and future directions in IQA research.

Abstract

Image quality assessment(IQA) is of increasing importance for image-based applications. Its purpose is to establish a model that can replace humans for accurately evaluating image quality. According to whether the reference image is complete and available, image quality evaluation can be divided into three categories: full-reference(FR), reduced-reference(RR), and non-reference(NR) image quality assessment. Due to the vigorous development of deep learning and the widespread attention of researchers, several non-reference image quality assessment methods based on deep learning have been proposed in recent years, and some have exceeded the performance of reduced -reference or even full-reference image quality assessment models. This article will review the concepts and metrics of image quality assessment and also video quality assessment, briefly introduce some methods of full-reference and semi-reference image quality assessment, and focus on the non-reference image quality assessment methods based on deep learning. Then introduce the commonly used synthetic database and real-world database. Finally, summarize and present challenges.