Limited-Reference Image Quality Assessment: Paradigms and Discussions

摘要

Image enhancement techniques play an important role in improving visual quality of media content. Image Quality Assessment (IQA) metrics are essential in comparing and improving image enhancement algorithms. Although these enhancement methods belong to different types of tasks in computer vision, the IQA for these methods has a common problem, namely, their reference information is limited. This poses a challenge to IQA: How to utilize the limited reference information to evaluate the qualities of distorted images. I am dedicated to approaching this challenge throughout my PhD. In this paper, first, I illustrate the motivation of my PhD project. Then, I formulate the problem and the ultimate goal of my PhD research. Next, I introduce some developed results in my research. Finally, I present my ongoing work and future directions.