Gradient-wise search strategy for blind image deblurring

Blind image deblurring is a long-standing challenging problem to improve the sharpness of an image as a prerequisite step. Many iterative methods are widely used for the deblurring image, but care must be taken to ensure that the methods have fast convergence and accuracy solutions. To address these problems, we propose a gradient-wise step size search strategy for iterative methods to achieve robustness and accelerate the deblurring process. We further modify the conjugate gradient method with the proposed strategy to solve the bling image deblurring problem. The gradient-wise step size aims to update gradient for each pixel individually, instead of updating step size by the fixed factor. The modified conjugate gradient method improves the convergence performance computation speed with a gradient-wise step size. Experimental results show that our method effectively estimates the sharp image for both motion blur images and defocused images. The results of synthetic datasets and natural images are better than what is achieved with other state-of-the-art blind image deblurring methods.

Application of Deep Learning-Based Methods to the Single Image Non-Uniform Blind Motion Deblurring Problem

In this paper, we present deep learning-based blind image deblurring methods for estimating and removing a non-uniform motion blur from a single blurry image. We propose two fully convolutional neural networks (CNN) for solving the problem. The networks are trained end-to-end to reconstruct the latent sharp image directly from the given single blurry image without estimating and making any assumptions on the blur kernel, its uniformity, and noise. We demonstrate the performance of the proposed models and show that our approaches can effectively estimate and remove complex non-uniform motion blur from a single blurry image.

Non-Blind Image Deblurring Method Using Shear High Order Total Variation Norm

In this paper, we propose a shear high-order gradient (SHOG) operator by combining the shear operator and high-order gradient (HOG) operator. Compared with the HOG operator, the proposed SHOG operator can incorporate more directionality and detect more abundant edge information. Based on the SHOG operator, we extend the total variation (TV) norm to shear high-order total variation (SHOTV), and then propose a SHOTV deblurring model. We also study some properties of the SHOG operator, and show that the SHOG matrices are Block Circulant with Circulant Blocks (BCCB) when the shear angle is [see formula in PDF]. The proposed model is solved efficiently by the alternating direction method of multipliers (ADMM). Experimental results demonstrate that the proposed method outperforms some state-of-the-art non-blind deblurring methods in both objective and perceptual quality.

Spectral Norm Regularization for Blind Image Deblurring

Blind image deblurring is a well-known ill-posed inverse problem in the computer vision field. To make the problem well-posed, this paper puts forward a plain but effective regularization method, namely spectral norm regularization (SN), which can be regarded as the symmetrical form of the spectral norm. This work is inspired by the observation that the SN value increases after the image is blurred. Based on this observation, a blind deblurring algorithm (BDA-SN) is designed. BDA-SN builds a deblurring estimator for the image degradation process by investigating the inherent properties of SN and an image gradient. Compared with previous image regularization methods, SN shows more vital abilities to differentiate clear and degraded images. Therefore, the SN of an image can effectively help image deblurring in various scenes, such as text, face, natural, and saturated images. Qualitative and quantitative experimental evaluations demonstrate that BDA-SN can achieve favorable performances on actual and simulated images, with the average PSNR reaching 31.41, especially on the benchmark dataset of Levin et al.

Dual Image Deblurring Using Deep Image Prior

Blind image deblurring, one of the main problems in image restoration, is a challenging, ill-posed problem. Hence, it is important to design a prior to solve it. Recently, deep image prior (DIP) has shown that convolutional neural networks (CNNs) can be a powerful prior for a single natural image. Previous DIP-based deblurring methods exploited CNNs as a prior when solving the blind deburring problem and performed remarkably well. However, these methods do not completely utilize the given multiple blurry images, and have limitations of performance for severely blurred images. This is because their architectures are strictly designed to utilize a single image. In this paper, we propose a method called DualDeblur, which uses dual blurry images to generate a single sharp image. DualDeblur jointly utilizes the complementary information of multiple blurry images to capture image statistics for a single sharp image. Additionally, we propose an adaptive L2_SSIM loss that enhances both pixel accuracy and structural properties. Extensive experiments show the superior performance of our method to previous methods in both qualitative and quantitative evaluations.

Deblurring Turbulent Images via Maximizing L1 Regularization

Atmospheric turbulence significantly degrades image quality. A blind image deblurring algorithm is needed, and a favorable image prior is the key to solving this problem. However, the general sparse priors support blurry images instead of explicit images, so the details of the restored images are lost. The recently developed priors are non-convex, resulting in complex and heuristic optimization. To handle these problems, we first propose a convex image prior; namely, maximizing L1 regularization (ML1). Benefiting from the symmetrybetween ML1 and L1 regularization, the ML1 supports clear images and preserves the image edges better. Then, a novel soft suppression strategy is designed for the deblurring algorithm to inhibit artifacts. A coarse-to-fine scheme and a non-blind algorithm are also constructed. For qualitative comparison, a turbulent blur dataset is built. Experiments on this dataset and real images demonstrate that the proposed method is superior to other state-of-the-art methods in blindly recovering turbulent images.