利用低秩先验的噪声模糊图像盲去卷积

单幅图像盲去卷积的目的是从一幅观测的模糊图像估计出模糊核和清晰图像。该问题是严重病态的,尤其是观测图像中噪声不可忽略时更具挑战性。该文主要针对如何有效利用低秩先验约束进行噪声模糊图像盲去卷积问题,提出一种在交替最大后验(MAP)估计框架下利用低秩先验约束的单幅噪声模糊图像盲去卷积方法。首先,在估计中间复原图像时,利用低秩先验约束对复原图像中的噪声进行抑制。然后,采用降噪后的中间复原图像估计模糊核,得到更好质量的模糊核估计。迭代上述两个操作获得最终可靠的模糊核估计。最后,根据所估计的模糊核,通过非盲去卷积方法复原出清晰图像。实验结果表明：所提方法在定量和定性评价指标上优于已有的代表性方法。     

An improved image blind deblurring based on dark channel prior

In order to solve the ringing effect caused by the incorrect estimation of the blur kernel, an improved blind image deblurring algorithm based on the dark channel prior is proposed. First, in the blur kernel estimation stage, high-pass filtering is introduced to enhance the image quality and enhance the edge information to make the blur kernel estimation more accurate. A combination of super Laplacian prior and dark channel prior is introduced to estimate the potential clear image. Then the accurate blur kernel is estimated through alternate iterations from coarse to fine. In the image restoration stage, a weighted least square filter is introduced to suppress the ringing effect of the original clear image to further improve the quality of image restoration. Finally, image deconvolution based on Laplace priors and L₀ regularized priors is used to restore clear images. Experimental results show that our approach improves the peak signal-to-noise ratio(PSNR) by about 0.4 d B and structural similarity(SSIM) by about 0.01, respectively. Compared with the existing image deblurring algorithms, this method can estimate the blur information more accurately, so that the restored image can achieve the effect of keeping the edges and removing ringing.     

Robust penalty-weighted deblurring via kernel adaption using single image

Image blind deconvolution is well known as a challenging, ill-posed problem due to the uncertainty of the blur kernel and the noise condition. Based on our observations, blind deconvolution algorithms tend to generate disconnected and noisy blur kernels, which would yield a serious ringing effect in the restored image if the input image is noisy. Therefore, there is still room for further improvement, especially for noisy images captured under poor illumination conditions. In this paper, we propose a robust blind deconvolution algorithm by adopting a penalty-weighted anisotropic diffusion prior. On one hand, the anisotropic diffusion prior effectively eliminates the discontinuity in the blur kernel caused by the noisy input image during the process of kernel estimation. On the other hand, the weighted penalizer reduces the speckle noise of the blur kernel, thus improving the quality of the restored image. The effectiveness of the proposed algorithm is verified by both synthetic and real images with defocused or motion blur.     

混合正则化约束的湍流退化图像复原算法

针对大气湍流引起的红外图像模糊问题,提出一种基于混合正则化的模糊核估计模型。根据图像主要边缘的稀疏性,采用图像梯度的L0范数为正则化项;通过分析模糊核的特性,提出能适用于复杂模糊情况的核L0-L2范数正则化约束。复原模型的优化过程中,结合变量分裂策略和增广拉格朗日法交替估计图像和模糊核,并利用快速傅里叶变换,实现模糊核的快速、准确估计;最终根据估计的模糊核,复原得清晰图像。实验结果表明,本文算法可以更好地复原退化图像,在主观视觉和客观质量评价方面都有所提高。     

Total variation blind deconvolution employing split Bregman iteration

Blind image deconvolution is one of the most challenging problems in image processing. The total variation (TV) regularization approach can effectively recover edges of image. In this paper, we propose a new TV blind deconvolution algorithm by employing split Bregman iteration (called as TV-BDSB). Considering the operator splitting and penalty techniques, we present also a new splitting objective function. Then, we propose an extended split Bregman iteration to address the minimizing problems, the latent image and the blur kernel are estimated alternately. The TV-BDSB algorithm can greatly reduce the computational cost and improve remarkably the image quality. Experiments are conducted on both synthetic and real-life degradations. Comparisons are also made with some existing blind deconvolution methods. Experimental results indicate the advantages of the proposed algorithm.     

Motion blur kernel estimation in steerable gradient domain of decomposed image

Blind deblurring, typically underdetermined or ill-posed problem, has attracted numerous research studies over the recent years. Various priors of either the image or the blur kernel are proposed to establish various regularization models to estimate the blur kernel. And sharp edges are often employed as an important clue to recover the blur kernel. However, due to the harmful effects caused by textures and various artifacts, sharp edges are not always beneficial to the kernel estimation. To address this problem, this paper presents a step-edge based blind image deblurring algorithm using steerable gradients. The proposed algorithm adopts a coarse-to-fine multiscale framework with step-edge restoration, kernel estimation and latent image estimation. In each scale, the step-edges are detected and refined through fast image decomposition and thresholding on steerable gradients, while the kernel and latent image are estimated by minimizing the quadratic energy functionals with steerable gradients. Because each of the minimizing functional has a closed-form solution, and can be implemented by using FFTs, our algorithm is also very fast. Experimental results on both synthetic and real data demonstrate that our method outperforms most existing single image blind deblurring methods.     

Kernel estimation from salient structure for robust motion deblurring

Blind image deblurring algorithms have been improving steadily in the past years. Most state-of-the-art algorithms, however, still cannot perform perfectly in challenging cases, especially in large blur setting. In this paper, we focus on how to estimate a good blur kernel from a single blurred image based on the image structure. We found that image details caused by blur could adversely affect the kernel estimation, especially when the blur kernel is large. One effective way to remove these details is to apply image denoising model based on the total variation (TV). First, we developed a novel method for computing image structures based on the TV model, such that the structures undermining the kernel estimation will be removed. Second, we applied a gradient selection method to mitigate the possible adverse effect of salient edges and improve the robustness of kernel estimation. Third, we proposed a novel kernel estimation method, which is capable of removing noise and preserving the continuity in the kernel. Finally, we developed an adaptive weighted spatial prior to preserve sharp edges in latent image restoration. Extensive experiments testify to the effectiveness of our method on various kinds of challenging examples.     

Blind image deconvolution for single motion-blurred image

Motion blur due to camera shake during exposure is one of the most common reasons of image degradation,which usually reduces the quality of photographs seriously.Based on the statistical properties of the natural image's gradient and the blur kernel,a blind deconvolution algorithm is proposed to restore the motion-blurred image caused by camera shake,adopting the variational Bayesian estimation theory.In addition,the ring effect is one problem that is not avoided in the process of image deconvolution,and usually makes the visual effect of the restored image badly.So a dering method is put forward based on the sub-region detection and fuzzy filter.Tested on the real blurred photographs,the experimental results show that the proposed algorithm of blind image deconvolution can remove the camera-shake motion blur from the degraded image effectively,and can eliminate the ring effect better,while preserve the edges and details of the image well.     

基于模糊结构图的模糊核估计

图像结构边缘对模糊核估计有重要意义.近年来许多成功的算法都致力从潜在清晰图像中分离出结构边缘形成中间图像,然后用其与模糊图像一起估计模糊核.但是这些算法忽视了从模糊图像中分离出结构边缘对应的部分,导致核估计过程中目标函数的数据项不平衡.针对这一问题,本文利用中间图像和潜在模糊核产生二值模板对模糊图像进行处理,分离出结构边缘对应的部分,并用其修正目标函数.此外本文提出采用L0范数同时约束幅值域和梯度域的正则项,从而缩小核估计的解空间.多个标准测试数据库上实验结果表面,本文算法无论在鲁棒性还是准确性方面均具有更好的效果.     

Spatially variant defocus blur map estimation and deblurring from a single image

In this paper, we propose a single image deblurring algorithm to remove spatially variant defocus blur based on the estimated blur map. Firstly, we estimate the blur map from a single image by utilizing the edge information and K nearest neighbors (KNN) matting interpolation. Secondly, the local kernels are derived by segmenting the blur map according to the blur amount of local regions and image contours. Thirdly, we adopt a BM3D-based non-blind deconvolution algorithm to restore the latent image. Finally, ringing artifacts and noise are detected and removed, to obtain a high quality in-focus image. Experimental results on real defocus blurred images demonstrate that our proposed algorithm outperforms some state-of-the-art approaches.     

Improved image deblurring based on salient-region segmentation

Image deblurring techniques play important roles in many image processing applications. As the blur varies spatially across the image plane, it calls for robust and effective methods to deal with the spatially-variant blur problem. In this paper, a Saliency-based Deblurring (SD) approach is proposed based on the saliency detection for salient-region segmentation and a corresponding compensate method for image deblurring. We also propose a PDE-based deblurring method which introduces an anisotropic Partial Differential Equation (PDE) model for latent image prediction and employs an adaptive optimization model in the kernel estimation and deconvolution steps. Experimental results demonstrate the effectiveness of the proposed algorithm.     

TDI遥感图像中畸变像移模糊的去除

采用离轴三反射结构的大视场空间相机存在较大的光学畸变,导致引入时间延迟积分(Time Delay Integration, TDI)技术的面阵探测器在推扫成像时产生像移模糊。根据畸变引起的TDI成像退化原理,将畸变像移模糊转化为非均匀运动模糊,通过求解像移路径计算初始模糊核,将其作为先验信息,建立半盲复原模型进一步细化模糊核。利用初始模糊核复原的粗略图像边缘指导模糊核的细化,提出一种多方向权重异性的全变差模型提取图像结构信息。为了增强先验信息对模糊核细化的约束,构建了含有初始模糊核的正则项,使模糊核的估计不过度依赖于图像内容,采用多尺度迭代方法求解。最后用正则化约束的非盲反卷积方法去除图像模糊。实验结果表明:与现有的几种去模糊算法相比,所提方法的去模糊效果不仅清晰自然且对不同样本图像的模糊核估计更稳定。     

基于变分贝叶斯估计的相机抖动模糊图像的盲复原算法

在曝光过程中由于相机抖动而导致的运动模糊,是一种常见的图像降质现象。该文提出了一种基于变分贝叶斯估计和自然图像梯度统计特性的盲复原算法,用于恢复相机抖动模糊图像,同时针对图像复原过程中出现的振铃效应,设计了一种基于分区域检测和Fuzzy滤波器的去振铃效应方法。实验结果表明,该文提出的盲复原算法能够有效地去除图像中因相机抖动而产生的模糊,而且在保持图像边缘和细节的同时,可以较好地降低振铃效应对图像复原质量的影响。     

Robust blind motion deblurring using near-infrared flash image

In light-limited situations, camera motion blur is one of the prime causes for poor image quality. Recovering the blur kernel and latent image from the blurred observation is an inherently ill-posed problem. In this paper, we introduce a hand-held multispectral camera to capture a pair of blurred image and Near-InfraRed (NIR) flash image simultaneously and analyze the correlation between the pair of images. To utilize the high-frequency details of the scene captured by the NIR-flash image, we exploit the NIR gradient constraint as a new type of image regularization, and integrate it into a Maximum-A-Posteriori (MAP) problem to iteratively perform the kernel estimation and image restoration. We demonstrate our method on the synthetic and real images with both spatially invariant and spatially varying blur. The experiments strongly support the effectiveness of our method to provide both accurate kernel estimation and superior latent image with more details and fewer ringing artifacts.     

Video super resolution based on non-local regularization and reliable motion estimation

Video super-resolution (SR) is a process for reconstructing high-resolution (HR) images by utilizing complementary information among multiple low-resolution (LR) images. Accurate estimation of the motion among the LR images significantly affects the quality of the reconstructed HR image. In this paper, we analyze the possible reasons for the inaccuracy of motion estimation and then propose a multi-lateral filter to regularize the process of motion estimation. This filter can adaptively correct motion estimation according to the estimation reliability, image intensity discontinuity, and motion dissimilarity. Furthermore, we introduce a non-local prior to solve the ill-posed problem of HR image reconstruction. This prior can fully utilize the self-similarities existing in natural images to regularize the HR image reconstruction. Finally, we employ a Bayesian formulation to incorporate the two regularizations into one Maximum a Posteriori (MAP) estimation model, where the HR image and the motion estimation can be refined progressively in an alternative and iterative manner. In addition, an algorithm that estimates the blur kernel by analyzing edges in an image is also presented in this paper. Experimental results demonstrate that the proposed approaches are highly effective and compare favorably to state-of-the-art SR algorithms.     

基于倒谱与频谱分析的模糊核估计算法

图像盲去模糊是典型的图像和信号处理问题,其目的是从模糊图像中恢复出模糊核及清晰图像。在模糊核估计方面,以往的算法通常将模糊核尺度作为必要的输入参数,近年来有些算法虽然能较准确的估计参数化模糊核,但不能有效估计自然模糊图像中普遍存在的非参数化模糊核。文中利用图像梯度倒谱估计模糊核后再利用频谱分析以进一步精确的估计小尺寸模糊核的尺度。实验结果表明,文中提出的方法能适用于绝大多数场景下自然模糊图像的模糊核尺度估计。     

Segmenting,removing and ranking partial blur

Image blur is a common phenomenon in daily life. Due to the great challenge, image restoration fascinates researchers to find out the solutions. Considering different types of blur, we propose a framework to segment the partial blur from a single image and then restore the latent information. In general, some morphological technologies are applied to separate the blur area. Traditionally, blind deconvolution method is applied in underdetermined conditions. In this research, we marginalize the kernel estimation by separating the problem into two stages, both of which are combined with different useful priors. A criterion of ranking the blur degree of a partial blur image is also proposed at the end of this paper. Experimental results demonstrate the accuracy and superiority of our approach.     

凹凸范数比值正则化的快速图像盲去模糊

模糊图像可表示为清晰图像和模糊核函数的卷积,由模糊图像恢复出清晰图像,需要同时估计模糊核和清晰图像,因此是一个病态问题.优化含有先验项的代价函数是求解病态问题最有效方法之一.针对图像盲去模糊问题,本研究提出具有更强稀疏表达能力的凹凸范数比值正则化先验项,在用变量分裂法求解模型时,提出用L1范数保真项更新估计图像,在更新模糊核时,提出使用线性递增权重参数对模糊核按多尺度方法由粗到细逐步估计,当获得模糊核后,利用封闭阈值公式估计清晰图像.该方法能快速得到高质量的清晰图像,实验结果验证了模型的有效性和算法的快速性.     

多尺度卷积神经网络的噪声模糊图像盲复原

图像盲复原是从一幅观测的模糊图像恢复出模糊核和清晰图像,传统盲去卷积算法采用简化模型估计模糊核,导致预测模糊核与真实值误差较大,最终复原结果不理想。针对此问题提出一种基于改进残差模块的多尺度卷积神经网络模型,采用端到端模式,无需估计模糊核。提出了一种基于限制网络输入的改进Wasserstein GAN （WGAN）,增加了一层输入限制层,能够限定参数初始值,提高了网络收敛速度。设计了多重损失函数,融合了基于多尺度网络的感知损失和基于条件式生成对抗网络的对抗损失。实验结果表明:所提方法在定量和定性评价指标上优于已有的代表性方法,并且运行速度比相近算法快了4倍。     

Total variation blind deconvolution

We present a blind deconvolution algorithm based on the total variational (TV) minimization method proposed by Acar and Vogel (1994). The motivation for regularizing with the TV norm is that it is extremely effective for recovering edges of images as well as some blurring functions, e.g., motion blur and out-of-focus blur. An alternating minimization (AM) implicit iterative scheme is devised to recover the image and simultaneously identify the point spread function (PSF). Numerical results indicate that the iterative scheme is quite robust, converges very fast (especially for discontinuous blur), and both the image and the PSF can be recovered under the presence of high noise level. Finally, we remark that PSFs without sharp edges, e.g., Gaussian blur, can also be identified through the TV approach.