Recent Progress in Image Deblurring

Abstract

This paper comprehensively reviews the recent development of image deblurring, including nonblind/blind, spatially invariant/variant deblurring techniques. Indeed, these techniques share the same objective of inferring a latent sharp image from one or several corresponding blurry images, while the blind deblurring techniques are also required to derive an accurate blur kernel. Considering the critical role of image restoration in modern imaging systems to provide high-quality images under complex environments such as motion, undesirable lighting conditions, and imperfect system components, image deblurring has attracted growing attention in recent years. From the viewpoint of how to handle the illposedness which is a crucial issue in deblurring tasks, existing methods can be grouped into five categories: Bayesian inference framework, variational methods, sparse representation-based methods, homographybased modeling, and region-based methods. In spite of achieving a certain level of development, image deblurring, especially the blind case, is limited in its success by complex application conditions which make the blur kernel hard to obtain and be spatially variant. We provide a holistic understanding and deep insight into image deblurring in this review. An analysis of the empirical evidence for representative methods, practical issues, as well as a discussion of promising future directions are also presented.

Accelerated Learning with Robustness to Adversarial Regressors

“…That is, using (70), and the value of a 0 , b 0 and c 0 as in (73), N 0 was determined. θ * is determined through (68), and θ 0 = 0. With a choice of = 10 −3 , the remaining parameters were calculated as in Figure 4, which led us to the hyperparameters as in (77) and (78).…”

“…We consider the non-blind deblurring problem framework [68], which consists on obtaining the best estimate of the original image X, given its blurry version B, and the known blur operator A. This is expressed with the following linear model:…”

Learning Blind Motion Deblurring

“…Blind image deblurring (BD) is quite common in real-world applications and has seen considerable progress in the last decade. A comprehensive review is provided in the recent overview article by Wang and Tao [29]. Traditional stateof-the-art methods such as Sun et al [26] or Michaeli and Irani [16] use carefully chosen patch-based priors for sharp image prediction.…”

Accelerating ℓ1−ℓ2 deblurring using wavelet expansions of operators

“…They were progressively replaced by more complicated nonlinear methods, incorporating prior knowledge on the image contents. We refer the interested reader to the following review papers [30,34,27] to get an overview of the available techniques.…”