Blind Image Deblurring: a Review
It provides a comprehensive overview for researchers in computer vision, but is incremental as a review paper.
This paper reviews the blind image deblurring problem, discussing its formulation, challenges, human vision insights, metrics, datasets, and typical optimization- and learning-based methods.
This is a review on blind image deblurring. First, we formulate the blind image deblurring problem and explain why it is challenging. Next, we bring some psychological and cognitive studies on the way our human vision system deblurs. Then, relying on several previous reviews, we discuss the topic of metrics and datasets, which is non-trivial to blind deblurring. Finally, we introduce some typical optimization-based methods and learning-based methods.