Recent Progress in Image Deblurring

• DOI: 10.48550/arxiv.1409.6838
• Publication Date: 2014-01-01
• Authors: Ruxin Wang; Dacheng Tao
• Keywords: Deblurring; Kernel (algebra); Latent image; Kernel density estimation

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