Blind-restoration-based blind separation method for permuted motion blurred images

A novel single-channel blind separation algorithm for permuted motion blurred images is proposed by using blind restoration in this paper. Both the motion direction and the length of the point spread function （PSF） are estimated by Radon transformation and extrema a detection. Using the estimated blur parameters, the permuted image is restored by performing the L-R blind restoration method. The permutation mixing matrices can be accurately estimated by classifying the ringing effect in the restored image, thereby the source images can be separated. Simulation results show a better separation efficiency for the permuted motion blurred image with various permutation operations. The proposed algorithm indicates a better performance on the robustness against Gaussian noise and lossy JPEG compression.

Anisotropic Total Variation Regularization Based NAS-RIF Blind Restoration Method for OCT Image

Based on anisotropic total variation regularization(ATVR), a nonnegativity and support constraints recursive inverse filtering(NAS-RIF) blind restoration method is proposed to enhance the quality of optical coherence tomography(OCT) image. First, ATVR is introduced into the cost function of NAS-RIF to improve the noise robustness and retain the details in the image.Since the split Bregman iterative is used to optimize the ATVR based cost function, the ATVR based NAS-RIF blind restoration method is then constructed. Furthermore, combined with the geometric nonlinear diffusion filter and the Poisson-distribution-based minimum error thresholding, the ATVR based NAS-RIF blind restoration method is used to realize the blind OCT image restoration. The experimental results demonstrate that the ATVR based NAS-RIF blind restoration method can successfully retain the details in the OCT images. In addition, the signal-to-noise ratio of the blind restored OCT images can be improved, along with the noise robustness.

Improved Multi-channel Blind Image Restoration Algorithm for UWB Radar

The imaging problem of low signal to noise ratio （SNR）echo is very important for ultra-wide band （UWB） through-wall radar. An improved multi-channel blind image restoration algorithm based on sub-space and constrained least square （CLS） is presented and applied to UWB radar system to deal with this issue. The high resolution of radar image is equivalent to multi-channel blind image restoration based on the improved model of the through-wall radar echo. And a new cost function is proposed to the multi-channel blind image restoration by considering the concept of sub-space as the limitation of blur identification. The proposed algorithm has all advantages of CLS and sub-space, and converts the image estimation to alternating-minimizing the two cost functions. Experimental results prove that the proposed algorithm is effective at improving the resolution of radar image even at low SNR.

Multichannel Blind CT Image Restoration via Variable Splitting and Alternating Direction Method

Computed tomography(CT) blurring caused by point spread function leads to errors in quantification and visualization. In this paper, multichannel blind CT image restoration is proposed to overcome the effect of point spread function. The main advantage from multichannel blind CT image restoration is to exploit the diversity and redundancy of information in different acquisitions. The proposed approach is based on a variable splitting to obtain an equivalent constrained optimization formulation, which is addressed with the alternating direction method of multipliers and simply implemented in the Fourier domain. Numerical experiments illustrate that our method obtains a higher average gain value of at least 1.21 d B in terms of Q metric than the other methods, and it requires only 7 iterations of alternating minimization to obtain a fast convergence.

Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network

Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.

Radial Basis Function Neural Network Based Super- Resolution Restoration for an Undersampled Image

To achieve restoration of high frequency information for an undersampled and degraded low-resolution image, a nonlinear and real-time processing method-the radial basis function (RBF) neural network based super-resolution method of restoration is proposed. The RBF network configuration and processing method is suitable for a high resolution restoration from an undersampled low-resolution image. The soft-competition learning scheme based on the k-means algorithm is used, and can achieve higher mapping approximation accuracy without increase in the network size. Experiments showed that the proposed algorithm can achieve a super-resolution restored image from an undersampled and degraded low-resolution image, and requires a shorter training time when compared with the multiplayer perception (MLP) network.

Fully 1×1 Convolutional Network for Lightweight Image Super-resolution

Deep convolutional neural networks,particularly large models with large kernels(3x3 or more),have achieved significant progress in single image super-resolution(SISR)tasks.However,the heavy computational footprint of such models prevents their de-ployment in real-time,resource-constrained environments.Conversely,1×1 convolutions have substantial computational efficiency,but struggle with aggregating local spatial representations,which is an essential capability for SISR models.In response to this dichotomy,we propose to harmonize the merits of both 3x3 and 1×1 kernels,and exploit their great potential for lightweight SISR tasks.Specific-ally,we propose a simple yet effective fully 1×1 convolutional network,named shift-Conv-based network(SCNet).By incorporating a parameter-free spatial-shift operation,the fully 1×1 convolutional network is equipped with a powerful representation capability and impressive computational efficiency.Extensive experiments demonstrate that SCNets,despite their fully 1×1 convolutional structure,consistently match or even surpass the performance of existing lightweight SR models that employ regular convolutions.The code and pretrained models can be found at .

Combination of super-resolution reconstruction and SGA-Net for marsh vegetation mapping using multi-resolution multispectral and hyperspectral images

Vegetation is crucial for wetland ecosystems.Human activities and climate changes are increasingly threatening wetland ecosystems.Combining satellite images and deep learning for classifying marsh vegetation communities has faced great challenges because of its coarse spatial resolution and limited spectral bands.This study aimed to propose a method to classify marsh vegetation using multi-resolution multispectral and hyperspectral images,combining super-resolution techniques and a novel self-constructing graph attention neural network(SGA-Net)algorithm.The SGA-Net algorithm includes a decoding layer(SCE-Net)to preciselyfine marsh vegetation classification in Honghe National Nature Reserve,Northeast China.The results indicated that the hyperspectral reconstruction images based on the super-resolution convolutional neural network(SRCNN)obtained higher accuracy with a peak signal-to-noise ratio(PSNR)of 28.87 and structural similarity(SSIM)of 0.76 in spatial quality and root mean squared error(RMSE)of 0.11 and R^(2) of 0.63 in spectral quality.The improvement of classification accuracy(MIoU)by enhanced super-resolution generative adversarial network(ESRGAN)(6.19%)was greater than that of SRCNN(4.33%)and super-resolution generative adversarial network(SRGAN)(3.64%).In most classification schemes,the SGA-Net outperformed DeepLabV3+and SegFormer algorithms for marsh vegetation and achieved the highest F1-score(78.47%).This study demonstrated that collaborative use of super-resolution reconstruction and deep learning is an effective approach for marsh vegetation mapping.

基于边缘约束与范数比值的图像盲复原

针对现有的研究方法对运动所引起的模糊图像进行复原时效果欠佳的问题,提出一种基于边缘约束与范数比值的图像盲复原算法.该算法首先对退化图像的边缘进行约束,得到图像的强边缘结构,提高了点扩散函数估计的准确率;然后对要估计的清晰图像构造范数比值的稀疏惩罚约束项,并将得到的强边缘信息与构造的范数比值惩罚约束项进行结合用于指引点扩散函数的复原;在对点扩散函数进行复原时,由粗到细多尺度交替迭代估计点扩散函数,使得迭代出的最大尺度更加精确;最后对图像进行非盲解卷积求解,使其复原.该算法将退化图像的边缘信息与构造的范数比值惩罚约束项进行结合指导点扩散函数的复原,可以抑制图像在复原过程中产生的大量伪迹.实验结果表明,该算法对恢复图像边缘细节具有很好的效果,可以得到优质的复原图像.

改进的局部最小像素先验遥感图像盲复原算法

为了解决遥感图像盲复原时模糊核估计不准确、复原图像存在振铃效应的问题,提出改进的局部最小像素先验遥感图像盲复原算法。该算法首先引入极端通道先验与局部最小像素先验结合,对图像的强度进行更好的约束,有利于得到更好的潜在清晰图像;然后采用基于梯度的方法估计模糊核,模糊核估计与中间潜在清晰图像估计交替迭代进行,获得较为理想的模糊核;最后引入联合双边滤波器,采用改进的拉普拉斯与正则化图像复原算法抑制图像复原的振铃效应。实验结果表明,本文方法对遥感图像复原效果较好,恢复的图像边缘清晰,振铃伪影得到抑制且模糊核较为理想;客观评价指标峰值信噪比(PSNR)较前沿复原算法平均提高约1.40 dB,结构相似度(SSIM)平均提高约0.02。

湍流退化图像复原技术研究

湍流退化图像复原技术旨在解决成像系统中因湍流效应引起的图像模糊和失真问题。本文介绍了湍流对图像影响的多种模型,包括Kolmogorov湍流模型、移动平均模型、Zernike多项式模型和平均结构函数模型。重点介绍了退化图像盲复原技术和深度学习的图像复原方法最新研究进展、课题组在该领域的研究进展和未来图像复原技术研究的方向。

Research on Adaptive Optics Image Restoration Algorithm Based on Improved Joint Maximum a Posteriori Method

In this paper, we propose a point spread function （PSF） reconstruction method and joint maximum a posteriori （JMAP） estimation method for the adaptive optics image restoration. Using the JMAP method as the basic principle, we establish the joint log likelihood function of multi-frame adaptive optics （AO） images based on the image Gaussian noise models. To begin with, combining the observed conditions and AO system characteristics, a predicted PSF model for the wavefront phase effect is developed; then, we build up iterative solution formulas of the AO image based on our proposed algorithm, addressing the implementation process of multi-frame AO images joint deconvolution method. We conduct a series of experiments on simulated and real degraded AO images to evaluate our proposed algorithm. Compared with the Wiener iterative blind deconvolution （Wiener-IBD） algorithm and Richardson-Lucy IBD algorithm, our algorithm has better restoration effects including higher peak signal-to-noise ratio （PSNR） and Laplacian sum （LS） value than the others. The research results have a certain application values for actual AO image restoration.

虚拟现实场景中模糊图像盲复原算法研究

在模糊图像盲复原处理中,如果忽略图像像素的权重,会导致复原后图像的结构相似度较低,于是提出虚拟现实场景中模糊图像盲复原算法。引入多尺度方法对目标图像进行分解,并估算每一层图像的模糊核。将模糊核作为输入值,运用NAS-RIF算法获取估计原始图像。根据图像匹配关系建立图像参考平面矩阵,设计虚拟现实图像融合算法。利用非局部均值原理算子,计算出图像中各像素的权重值,再结合图像稀疏度构建图像盲复原模型。仿真结果表明,所提算法复原后图像的平均结构相似度为0.94,结构相似度得到了提升,并且图像复原质量较高。

基于深度先验的盲图像去模糊算法

盲图像去模糊旨在模糊核未知的情况下从模糊图像恢复清晰图像,这是一个欠定逆问题,需要引入图像先验信息限定解空间.受到SelfDeblur的启发,本文提出了一种基于深度先验的盲图像去模糊算法,结合深度网络与正则化模型对清晰图像与模糊核联合建模,交替迭代估计清晰图像与模糊核.在图像估计子问题中,模糊核参与RGB三通道损失函数的约束下,利用隐含图像平滑性约束的深度卷积神经网络DIP-Net生成清晰图像;在模糊核估计子问题中,直接求取模糊核正则化约束模型的全局极小解,不同于SelfDeblur的全连接网络使用梯度下降法更新模糊核.本文算法结合深度网络实现正则化方法,与监督学习相比,无需成对的模糊/清晰图像数据集训练网络;与传统模型方法相比,无需通过多级金字塔的方式由粗到细地估计模糊核.在模拟与真实模糊图像上的实验结果表明;本文算法能够快速、准确地估计出清晰图像和模糊核,并能够有效抑制图像复原过程中存在的噪声放大问题.

基于快速盲复原法的激光视频监控图像光斑定位研究

图像中存在光斑会极大程度降低图像质量,准确定位光斑能够改善这种情况,提出了基于快速盲复原法的激光视频监控图像光斑定位方法。首先采集视频监控系统激光图像,利用透视变换原理转换坐标系实现红外图像与可见光图像之间的配准,然后利用快速盲复原法迅速复原配准后的激光图像并且分割光斑目标区域实现光斑目标特征提取,对提取到的特征进行识别,采用F.Leber l模型展开计算,确定光斑中心位置。最后实验结果表明,利用该方法配准和处理图像时能够获得较为清晰的激光图像,提升特征提取的准确性,准确性最大值为98.46%,耗时较少,最大值仅为3 s,且具有较高的抗噪性能高。

基于非线性信道先验的水下盲图像复原方法

为了将水流干扰下的运动模糊图像恢复成清晰图像,提出基于非线性信道先验的水下盲图像复原方法。第一,利用差异通道增益对红色通道进行初始补偿,估计出精确的环境背景光;第二,求取红通道的粗略传输图,对初始传输图进行导向滤波处理得到精准的透射率;第三,在红、绿、蓝三通道中附加各自通道的环境背景光来统一上述透射率,利用补偿屏蔽的方式合并得到去雾的水下盲图像;第四,基于非线性信道先验获得去雾水下盲图像的初始复原图像,将初始复原图像、模糊核以及潜在清晰图像经过多次迭代计算得到最终的水下复原图像。实验结果表明,与水下暗通道先验算法、水下retinex增强以及水下归一化总变分方法相比,所提方法在Ancuti数据集上的水下图像评价指标值分别提升了21.7%、10.9%、26.5%,对水流干扰下的运动模糊图像有较好的复原效果。

盲图像复原研究现状

盲图像复原是在未知或不完全确知相关原始图像与成像点扩展函数的先验知识的情形下,利用所观测到的降质图像对原始图像和点扩展函数进行估计的一种图像处理方法。本文对近年来涌现出的主要盲图像复原算法进行了回顾,并根据相应的理论来源及相互联系将其划分为四大类,对各类复原算法及其改进算法进行了分析和讨论,为更清晰与深刻地认识和理解盲图像复原理论、解决实际图像降质问题提供参考。

基于小波变换的正则化盲图像复原算法

提出了一种将小波变换和自适应正则化方法相结合的盲图像复原算法。该算法先对退化后的图像进行小波分解,得到图像在不同子频段的信息;然后针对各个子频段内图像的频率和方向特性,使用不同的自适应正则化复原方法,在图像的低频子频段进行去模糊;高频子频段则进行抑制噪声和保边缘特征;最后通过小波逆变换得到复原后的图像。实验结果表明,MSE减少了1.60,信噪比增量为1.76,算法性能和复原效果相对空间自适应正则化方法,都有一定的提高。

基于归一化超拉普拉斯先验项的运动模糊图像盲复原

基于变分方法提出了一种运动模糊退化图像的盲复原算法。考虑自然场景的图像梯度符合长拖尾概率分布,提出的方法采用归一化的超拉普拉斯先验项作为变分能量方程中的光滑项,从而有利于图像在去模糊的求解过程中正确解收敛。由于建立的能量方程不是严格凸的函数,故引入了分裂方法进行求解。整个运动模糊退化图像的盲复原过程在多尺度框架下由粗到细尺度渐进执行。最后利用估计出的点扩展函数计算清晰图像。相对于传统的盲复原算法,本文提出的算法不需要预测图像的梯度信息和对梯度进行筛选,直接求解能量方程就能够得到相应的正确解。得到的结果验证了本文算法的有效性。

空间变化PSF非盲去卷积图像复原法综述

传统的图像复原一般认为点扩散函数(PSF)是空间不变的,实际光学系统由于受到像差等因素的影响,并非严格的线性空间不变系统,基于空间变化PSF的非盲去卷积图像复原法逐渐体现其优越性。空间变化PSF的非盲去卷积图像复原法先准确估计图像空间变化的PSF,再利用非盲去卷积算法对图像进行复原,有利于恢复出高质量图像。本文从算法的角度综述了近几年提出的基于空间变化PSF的非盲去卷积图像复原方法,并对比了基于强边缘预测估计PSF的非盲去卷积法、基于模糊噪声图像对PSF估计非盲去卷积法等算法的优缺点,各算法分别在PSF估计精确度、振铃效应抑制效果、适用范围等方面体现出各自的优劣。空间变化PSF的非盲去卷积图像复原法的研究,有利于推进图像复原技术向更高水平发展,使光学系统往轻小型化方向发展,从而在多个科学领域发挥其重要作用。