亥姆霍兹涡量方程与偏微分方程耦合修复模型

提出一种基于图像几何特征的形态学不变的耦合修复模型。耦合模型使用流体力学中无粘度亥姆霍兹涡量方程平滑的修复图像缺失信息区域。本文证明了亥姆霍兹涡量方程与传输平滑度信息的图像修复模型的等价性。曲率是图像几何特征作用的结果,本文提出沿等照度线方向传输曲率信息的三阶形态学不变偏微分方程,并将抑制涡量的无粘亥姆霍兹方程和正向传输曲率信息的三阶偏微分方程耦合。耦合模型平滑的修复图像并保持图像中的线性特征。理论和实验证明了本文提出的耦合模型在图像修复中的有效性。     

一种改进的二阶偏微分去噪模型

分析了基于二阶偏微分的扩散方程模型的基本原理,针对该模型在去噪的同时会产生阶梯效应的缺点,提出了一种基于图像结构信息的二阶偏微分去噪模型。在该模型中,在二阶偏微分的全变分模型的正则化项加入图像的切矢量和法矢量信息,并由此推导出相应的扩散方程,再对扩散方程的扩散强度因子进行修改。在实验中,将模型分别与基于二阶偏微分、四阶偏微分的全变分模型进行对比分析表明,实验结果证明该模型能有效地去除图像噪声,克服阶梯效应的产生,主观性能最优。     

基于结构分量和信息熵的Criminisi图像修复算法

针对Criminisi图像修复算法中优先级计算易受 图像纹理影响的问题,提出了改 进的基于图像结构分量的优先级函数。首先采用变分分解模型,将待修补图像分解为结构分 量和 纹理分量;其次基于结构分量计算数据项,排除纹理的影响;然后在优先权函数中 引入度量像素块复杂度的信息熵,将像素块中除了中心点之外其它位置的结构信息 融 入到优先权的计算中,使修补次序进一步向结构丰富的像素块倾斜;最后将优先权函数 表 示为置信度、数据项和信息熵的加权和,以解决传统Criminisi算法优先权随着置信度 迅速 下降为零而造成修复次序出现偏差的不足。新的优先权函数排除了像素块中在计算数据项时 纹 理的影响,并且融合更多的结构信息,使修复次序更加准确。实验结果表明,对于 不 同的人工图像和自然图像,本文模型都能取得较为满意的修复结果。     

基于三通道多小波紧标架的图像曲率修复模型

为解决正交小波域图像修复方法的现存小波 系数不能提供丢 失小波系数的充足信息问题,将曲率修复(CDD)模型扩展到非正交小波域,提出一种新的基 于三通道多小波 紧标架的图像CDD模型。进一步考虑到CDD模型的等照度线是按照直线连接的问 题,提出了一种新的CCD模型。新模型的修复在两个方向上进行,在法向上按照改进的曲率 函数进行修复, 在切向上实现输运机制。新模型结合了多小波紧标架分解技术和改进的CDD模型的 优势,利用标架域中 小波系数之间具有的冗余性对缺损的信息进行弥补,对现有CDD模型进行改进。给出了 有效的split Bregman 仿真算法,并采用不同的图像进行了仿真。实验结果表明,新模型对大面积缺损修复及噪声 抑制都具有良好 的修复效果,即使在大量小波系数丢失的情况下,也能保持图像的边缘结构等几何特征,大 大的改善修复质量。     

一种基于TV-Stokes方程的图像修复算法

讨论使用TV-Stokes方程进行图像修复,通过把等照度线方向传输进入修复区域,用能量最小化模型和零散度条件,获得一个非线性的Stokes方程.一旦构造了等照度线,图像就以等照度线方向修复.     

空间差异度量约束的图像修复

针对传统算法在图像修复时选取最佳块匹配准则的单一性和随机性的问题,提出了一种空间差异度量约束的图像修复方法。该算法利用等照度线确定待修复块的优先级,根据空间差异度量约束的最佳块匹配准则搜索与该待修复块最匹配的样本块,采用最佳匹配块的信息更新优先级最高的待修复块的信息以修复其缺失像素信息。实验结果表明,与传统算法相比,所提算法能有效提高图像修复的主客观质量,对三种类型的信息缺失均取得了较好的修复效果。     

A Novel Coupled Bi-directional Diffused Image Inpainting Model with Morphological Invariant Property

In this paper, a novel coupled inpainting model which bi-directionally diffuses image information is proposed. It is morphological invariant which restores the target region based on geometric property. The image information is diffused along both the direction normal to edges and along isophotes. Total variation （TV） model is used to diffuse along the direction normal to edges which reconnects the broken lines in the target region directly. The along isophotes diffused part is the inviscid Helmholtz vorticity equation in fluid dynamics. The Helmholtz equation diffuses a smooth measure of image along isophotes, and it is morphological invariant. The novel model is comprised by 2nd order Partial differential equations （PDEs）, so the numerical scheme of it is simple and the processing time is limited. Experimental results demonstrate that the novel model smoothly restores the target region by diffusing along two orthogonal directions and preserves the linear structure which leads to its better performance than conventional inpainting models.     

数字图像处理中的偏微分方程方法

图像是获取信息的重要媒介,图像处理技术广泛用于人类生活及社会生产中.偏微分方程是一种数学分析方法,并且它的特性由扩散方向和扩散项决定,这一点对图像处理大为有利.本文综述了近年来受到广泛重视的数字图像处理中的偏微分方程方法.给出了偏微分方程在图像去噪、图像放大、图像分割、图像修复中主要算法的优势及不足,同时给出了我们的改进算法,并展示了实验结果.     

Face completion with Hybrid Dilated Convolution

Image completion is a challenging task which aims to fill the missing or masked regions in images with plausibly synthesized contents. In this paper, we focus on face image inpainting tasks, aiming at reconstructing missing or damaged regions of an incomplete face image given the context information. We specially design the U-Net architecture to tackle the problem. The proposed U-Net based method combines Hybrid Dilated Convolution (HDC) and spectral normalization to fill in missing regions of any shape with sharp structures and fine-detailed textures. We perform both qualitative and quantitative evaluation on two challenging face datasets. Experimental results demonstrate that our method outperforms previous learning-based inpainting methods. The proposed method can generate realistic and semantically plausible images.     

局部特征分类的自适应扩散模型

本文提出了一种既能保持图像特征又能加快扩散速度的自适应扩散模型。首先,该模型利用平均梯度矩阵的特征值区分出图像的平坦区域、线条边缘和角点;其次,该模型根据平均梯度矩阵及其特征向量来控制图像信息的扩散方向;这样,该模型可以在不同的区域自适应地选择不同的扩散方向和扩散速度,从而很好地保持了图像特征并自适应地加快了扩散速度。实验结果表明,该模型可以保持图像结构特征,抑制噪声,应用到数字图像修复中,既能加快图像修复速度,又能使修复后的图像具有更好的视觉效果。      

一种改进的BSCB图像修补算法

针对传统BSCB算法对颜色复杂度高或缺损区域较大的图像修补效果较差的问题,提出一种改进的BSCB图像修补算法.考虑传统算法中初始化、光滑算子和修补扩散等步骤中存在的缺陷,分别对其进行了改进.改进的BSCB算法进行图像修补时,采用随机初始化方法,引入平滑和梯度算子代替原拉普拉斯图像平滑算子,并采用加权平均算法选择所有邻点进行异向性扩散,从而得到最终修补结果.实验表明,新方法修补图像,特别是修补颜色复杂度高、缺损区域较大的图像具有较好的效果.     

Hybrid error concealment method combining exemplar-based image inpainting and spatial interpolation

This paper proposes an efficient error concealment method for the reconstruction of pixels that are lost in video communication. The proposed method is developed by combining exemplar-based image inpainting for patch reconstruction and spatial interpolation for pixel reconstruction using adaptive threshold by local complexity. By exemplar-based image inpainting, regions with regular structures are reconstructed. For complex regions with irregular structures, just one pixel is reconstructed using the proposed spatial interpolation method. The proposed spatial interpolation method performs reconstruction by selecting adaptively directional interpolation or neighbor interpolation based on gradient information. Simulation results show that the proposed hybrid method performs reconstruction with significantly improved subjective quality compared with the previous spatial error concealment and image inpainting methods. The proposed method also gives substantial improvements of PSNR compared with the previous methods.     

改进的TV-Stokes图像修复模型及其算法

该文在研究图像修复的基础上,提出了一种改进的TV-Stokes图像修复模型。通过分析新模型的性质,给出一种高效且快速的数值算法。由于新模型耦合了两个变量,因此新算法首先采用交替迭代策略化原问题为两个去耦的次问题,然后再对两个次问题分别利用对偶方法和分裂Bregman方法进行数值求解。实验结果表明该文所提出的算法不但修复图像的效果较好,而且修复的速度较快。     

基于双向模糊扩散的保持特征的图像锐化

本文基于模糊集合理论,提出了一个双向模糊扩散框架.这个框架沿着等照度线(边缘)的梯度方向实施模糊的反向扩散;而相反地沿切线方向实施确定的正向扩散.为了保持图像特征的自然过渡,利用图像的局部结构张量的特征值检测图像的不同特征,并进行相应的锐化处理.     

Detail retaining convolutional neural network for image denoising

Compared with the traditional image denoising method, although the convolutional neural network (CNN) has better denoising performance, there is an important issue that has not been well resolved: the residual image obtained by learning the difference between noisy image and clean image pairs contains abundant image detail information, resulting in the serious loss of detail in the denoised image. In this paper, in order to relearn the lost image detail information, a mathematical model is deducted from a minimization problem and an end-to-end detail retaining CNN (DRCNN) is proposed. Unlike most denoising methods based on CNN, DRCNN is not only focus to image denoising, but also the integrity of high frequency image content. DRCNN needs less parameters and storage space, therefore it has better generalization ability. Moreover, DRCNN can also adapt to different image restoration tasks such as blind image denoising, single image superresolution (SISR), blind deburring and image inpainting. Extensive experiments show that DRCNN has a better effect than some classic and novel methods.     

An efficient framework for image/video inpainting

Image inpainting has been widely applied to many applications, such as restoring corrupted old photos, erasing video logos, concealing errors in a digital video processing system, and so on. However, traditional geometric inpainting methods suffer low efficiency. To tackle this problem, this paper addresses an efficient transform based framework for geometric methods. Given an image, we firstly decompose it, then separately perform restoration process and finally employ Laplacian diffusion function to hold local texture coherence. Experimental results show that the proposed method not only speeds up and enhances the performances of geometric methods, but also obtains a better restoration results compared with the traditional texture and hybrid methods.     

Image segmentation and inpainting using hierarchical level set and texture mapping

Image inpainting is an artistic procedure to recover a damaged painting or picture. We propose a novel approach for image inpainting by using the Mumford-Shah (MS) model and the level set method to estimate image structure of the damaged regions. This approach has been successfully used in image segmentation problem. Compared to some other inpainting methods, the MS model approach detects and preserves edges in the inpainting areas. We propose a fast and efficient algorithm that achieves both inpainting and segmentation. In previous works on the MS model, only one or two level set functions are used to segment an image. While this approach works well on simple cases, detailed edges cannot be detected in complicated image structures. Although multi-level set functions can be used to segment an image into many regions, the traditional approach causes extensive computations and the solutions depend on the location of initial curves. Our proposed approach utilizes faster hierarchical level set method and guarantees convergence independent of initial conditions. Because we detect both the main structure and the detailed edges, our approach preserves edges in the inpainting area. Also, exemplar-based approach for filling textured regions is employed. Experimental results demonstrate the advantage of our method.     

Generative image inpainting with salient prior and relative total variation

Image inpainting is an important research direction of image processing. The generative adversarial network (GAN), which can reconstruct new reasonable content in the corrupted region, is the most interesting tool in current inpainting technologies. However, the previous deep methods generally need to be pre-added the binary mask representing the corruption location as the extra input. A novel inpainting algorithm which does not require additional external labels is proposed in this paper. The algorithm consists of two parts: corruption recognition module and content inpainting module, which can recognize and fill random corruption. In the recognizer, the salient object from the uncorrupted region is used as the prior for distinguishing corruption. In the inpainting module, a two-stage network is applied to reconstruct the image from coarse content to texture details. To avoid the misdetection in recognition which has a negative impact on the restoration in inpainting, we perform relative total variational filtering on the corrupted image, and use the salient map as the supervision of detail reconstruction. Qualitative and quantitative experiments on multiple datasets verify the effectiveness of our recognition module, the competitive advantage of our inpainting module, and the enlightening significance of our total algorithm in image inpainting.     

基于Navier-Stokes方程的视频去隔行方法

随着技术的发展,常需将已有的隔行视频转换成高质量的逐行视频。本文提出一种基于Navier-Stokes（N-S）方程的视频去隔行方法。将基于N-S方程的图像修复模型应用到视频空间,由理想三维流体方程,建立视频的局部约束条件;然后,根据其各向异性特征,导出单个像素点的修复方程;最后,通过对隔行视频间隔区域的逐点修复,实现视频去隔行。实验表明,本文方法能够较好的抑制运动虚像和边沿锯齿。      

FFTI: Image inpainting algorithm via features fusion and two-steps inpainting

In view of the faultiness that the existing image inpainting methods fail to make full use of the complete region to predict the missing region features when the object features are seriously missing, resulting in discontinuous features and fuzzy detail texture of the inpainting results, a fine inpainting method of incomplete image based on features fusion and two-steps inpainting (FFTI) is proposed in this paper. Firstly, the dynamic memory networks (DMN+) are used to fuse the external features and internal features of the incomplete image to generate the incomplete image optimization map. Secondly, a generation countermeasure generative network with gradient penalty constraints is constructed to guide the generator to rough repair the optimized incomplete image and obtain the rough repair map of the target to be repaired. Finally, the coarse repair graph is further optimized by the idea of coherence of relevant features to obtain the final fine repair graph. It is verified by simulation on three image data sets with different complexity, and compared with the existing dominant repair model for visual effect and objective data. The experimental results show that the results of the model repair in this paper are more reasonable in texture structure, better than other models in visual effect and objective data, and the Peak Signal-to-Noise Ratio of the proposed algorithm in the most challenging underwater targe dataset is 27.01, the highest Structural Similarity Index is 0.949.