Learn from the past – sequentially one-to-one video deblurring network

With the growing availability of hand-held cameras in recent years, more and more images and videos are taken at any time and any place. However, they usually suffer from undesirable blur due to camera shake or object motion in the scene. In recent years, a few modern video deblurring methods are proposed and achieve impressive performance. However, they are still not suitable for practical applications as high computational cost or using future information as input. To address the issues, we propose a sequentially one-to-one video deblurring network (SOON) which can deblur effectively without any future information. It transfers both spatial and temporal information to the next frame by utilizing the recurrent architecture. In addition, we design a novel Spatio-Temporal Attention module to nudge the network to focus on the meaningful and essential features in the past. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art deblurring methods, both quantitatively and qualitatively, on various challenging real-world deblurring datasets. Moreover, as our method deblurs in an online manner and is potentially real-time, it is more suitable for practical applications.     

Experimental study on the application of a compressed-sensing (CS)-based deblurring method in x-ray nondestructive testing and its image performance

We investigated the compressed-sensing (CS)-based deblurring framework incorporated with the total-variation (TV) regularization penalty for effective image deblurring of high accuracy in x-ray imaging. We implemented the proposed algorithm and performed a systematic experiment to demonstrate its viability for image deblurring in x-ray nondestructive testing. We obtained x-ray images of several selected electronic components at an x-ray tube condition of 80 kV_p and 1.25 mAs and investigated the imaging characteristics in terms of the noise power spectrum and the modulation. We expect the proposed deblurring method to be applicable to improve the image characteristics considerably in x-ray nondestructive testing.     

用迭代法消除数字图像放大后的模糊

用迭代法对数字图像经过插值放大后产生的模糊问题进行了研究，把数字图像插值放大造成的模糊看成是点扩散函数与清晰图像卷积的结果，根据插值算法可以得到点扩散函数，由于数字图像解卷积是典型的解线性方程组的问题，用雅可比（Jacobi）迭代法得到了很好的结果。与频谱空间变换的方法相比，迭代法没有分母为0的问题和空间变换过程造成的舍入误差。     

基于深度编码–解码器的图像模糊核估计

在图像去模糊问题中,显著边缘结构对图像的模糊核估计具有重要的作用.本文提出一种基于深度编码-解码器的图像模糊核估计算法.首先,通过构建训练数据集对深度编码-解码器进行训练,进而自适应地获得模糊图像的显著边缘结构;接着,结合显著边缘结构和模糊图像,利用L2范数正则化对模糊核进行估计;最后,利用超拉普拉斯先验和所估计的模糊核对清晰图像进行估计.与传统的方法相比,所提出的方法不需要多尺度迭代框架.实验结果表明,所提出的算法在获得较好的显著边缘结构以及清晰图像的同时,能够减少算法计算的时间.     

图像组转置训练及非凸约束的去噪去模糊算法

针对稀疏表示模型的过完备字典集训练过程中图像块采样不充分问题,提出图像组转置训练及非凸约束的去噪去模糊算法.采用组间方差约束的图像块搜索策略,并根据自适应软阈值对筛选的字典集进行转置学习.在重构过程中采用l_p(0范数约束以保证结果的强稀疏性.最后采用Bregman拆分迭代法求解文中非凸模型.实验表明,文中算法重构图像具有较好的视觉效果,去噪去模糊效果较优.     

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.     

Robust Remove Noise Using Multiple Degraded Images

In this paper, we propose a model to remove noise or deblurring by multiple degraded images. In the algorithm, we introduce robust L1 norm data fidelity term and bilateral total variation regularization term. Experimental results show that our algorithm is effective.     

Image deblurring with computer generated double phase holograms

We explore a method of producing a deblurring filter developed by Hsueh and Sawchuk which uses two unit vectors in each cell of a computer generated hologram, to give on addition, both the amplitude and phase of the required filter function, the amplitude being scaled to be less than one. The resolution of such a filter is limited by the quantization errors in drawing the hologram. We suggest a method for reducing this error by reducing the amplitude contrast range of the filter, while maintaining its phase range. The filter is then backed with an amplitude only filter to correct for this reduction of the amplitude range. Experiments show a clear improvement in resolution in the second case. The original computer generated hologram filter has also been heterodyned to give a much increased space bandwidth product and used to deblur a large object.     

Enhancing Bayesian Estimators for Removing Camera Shake

The aim of removing camera shake is to estimate a sharp version x from a shaken image y when the blur kernel k is unknown. Recent research on this topic evolved through two paradigms called and . only solves for k by marginalizing the image prior, while recovers both x and k by selecting the mode of the posterior distribution. This paper first systematically analyses the latent limitations of these two estimators through Bayesian analysis. We explain the reason why it is so difficult for image statistics to solve the previously reported failure. Then we show that the leading methods, which depend on efficient prediction of large step edges, are not robust to natural images due to the diversity of edges. , although much more robust to diverse edges, is constrained by two factors: the prior variation over different images, and the ratio between image size and kernel size. To overcome these limitations, we introduce an inter‐scale prior prediction scheme and a principled mechanism for integrating the sharpening filter into . Both qualitative results and extensive quantitative comparisons demonstrate that our algorithm outperforms state‐of‐the‐art methods.     

Ultrasound image restoration based on a learned dictionary and a higher-order MRF

The restoration of images degraded by blur and multiplicative noise is a critical preprocessing step in medical ultrasound images which exhibit clinical diagnostic features of interest. This paper proposes a novel non-smooth non-convex variational model for ultrasound images denoising and deblurring motivated by the successes of sparse representation of images and FoE based approaches. Dictionaries are well adapted to textures and extended to arbitrary image sizes by defining a global image prior, while FoE image prior explicitly characterizes the statistics properties of natural image. Following these ideas, the new model is composed of the data-fidelity term, the sparse and redundant representations via learned dictionaries, and the FoE image prior model. The iPiano algorithm can efficiently deal with this optimization problem. The new proposed model is applied to several simulated images and real ultrasound images. The experimental results of denoising and deblurring show that proposed method gives a better visual effect by efficiently removing noise and preserving details well compared with two state-of-the-art methods.