Point-and-edge model for edge-preserving splatting

We introduce the point-and-edge model for edge-preserving modeling and rendering. Besides a set of surface points, the point-and-edge model also includes edge points representing the sharp edges in the model. The surface points and the sharp edges are relatively independent of each other. We present a feedback algorithm to simplify the point-and-edge model with bounded error based on an edge-preserving clustering method. An efficient constrained splatting method is used to preserve the sharp edges in the rendering, regardless of the surface point density.     

Near-recursive optical flow from weighted image differences.

This correspondence derives a formal link between temporally weighted frame differences, or disturbance fields, which carry limited information suitable for motion detection, and the optic flow (OF), which carries richer information on local image motion. We use this link to derive a novel, simple, near-recursive optic flow algorithm based on a recursive-filter formulation. Most quantities involved are computed recursively, using only data from the current and previous frame. We can limit expensive OF calculations to pixels where motion magnitude is sufficiently high using image differences which the algorithm computes anyway. Experimental results with well-known synthetic, ground-truthed test sequences and standard performance metrics indicate good quantitative performance. Tests with real sequences suggest similar or better performance than a well-known, similar algorithm due to Lucas and Kanade (LK).     

混合特性正则化约束的运动模糊盲复原

目的 为了提高运动模糊图像盲复原清晰度,提出一种混合特性正则化约束的运动模糊盲复原算法。方法 首先利用基于局部加权全变差的结构提取算法提取显著边缘,降低了噪声对边缘提取的影响。然后改进模糊核模型的平滑与保真正则项,在保证精确估计的同时,增强了模糊核的抗噪性能。最后改进梯度拟合策略,并加入保边正则项,使图像梯度更加符合重尾分布特性,且保证了边缘细节。结果 本文通过两组实验验证改进模型与所提算法的优越性。实验1以模拟运动模糊图像作为实验对象,通过对比分析5种组合步骤算法的复原效果,验证了本文改进模糊核模型与改进复原图像模型的鲁棒性较强。实验结果表明,本文改进模型复原图像的边缘细节更加清晰自然,评价指标明显提升。实验2以小型无人机真实运动模糊图像为实验对象,通过与传统算法进行对比,对比分析了所提算法的鲁棒性与实用性。实验结果表明,本文算法复原图像的标准差提升约11.4%,平均梯度提升约30.1%,信息熵提升约2.2%,且具有较好的主观视觉效果。结论 针对运动模糊图像盲复原,通过理论分析和实验验证,说明了本文改进模型的优越性,所提算法的复原效果较好。     

Linearized proximal alternating minimization algorithm for motion deblurring by nonlocal regularization

Non-blind motion deblurring problems are highly ill-posed and so it is quite difficult to find the original sharp and clean image. To handle ill-posedness of the motion deblurring problem, we use nonlocal total variation (abbreviated as TV) regularization approaches. Nonlocal TV can restore periodic textures and local geometric information better than local TV. But, since nonlocal TV requires weighted difference between pixels in the whole image, it demands much more computational resources than local TV. By using the linearization of the fidelity term and the proximal function, our proposed algorithm does not require any inversion of blurring operator and nonlocal operator. Therefore, the proposed algorithm is very efficient for motion deblurring problems. We compare the numerical performance of our proposed algorithm with that of several state-of-the-art algorithms for deblurring problems. Our numerical results show that the proposed method is faster and more robust than state-of-the-art algorithms on motion deblurring problems.     

多分辨率LK光流联合SURF的跟踪方法

针对交通监控中运动目标形变、雾霾天气、高速、光照不均、部分遮挡等复杂情况导致Lucas-Kanade（LK）算法跟踪不稳定问题,提出基于多分辨率LK光流算法联合快速鲁棒性特征（SURF）的跟踪算法。所提算法构建图像多分辨率小波金字塔,解决传统LK算法中同一像素点帧间大尺度运动易丢失问题;同时联合SURF尺度不变特征变换算法,提取特征点进行光流跟踪,并制定自适应模板实时更新策略;在减少光流计算量的同时增强运动目标抗复杂环境的能力。实验结果表明,新方法中特征点匹配准确快速,自适应性强,在交通复杂化境中跟踪稳定。     

Hyperparameter estimation for satellite image restoration using a MCMC maximum-likelihood method

The satellite image deconvolution problem is ill-posed and must be regularized. Herein, we use an edge-preserving regularization model using a ? function, involving two hyperparameters. Our goal is to estimate the optimal parameters in order to automatically reconstruct images. We propose to use the maximum-likelihood estimator (MLE), applied to the observed image. We need sampling from prior and posterior distributions. Since the convolution prevents use of standard samplers, we have developed a modified Geman-Yang algorithm, using an auxiliary variable and a cosine transform. We present a Markov chain Monte Carlo maximum-likelihood (MCMCML) technique which is able to simultaneously achieve the estimation and the reconstruction.     

Total variation constraint GAN for dynamic scene deblurring

Recovering the sharp image solely from the blurry image in dynamic scene is challenging due to the ill-defined nature of the problem. Through Wasserstein distance and L₁ norm of total variation combined regularization, we propose a novel TV-DRGAN optimization framework to obtain a latent sharp image from some observed blurry images. Our method benefits from two aspects: one is the improved object total variation energy to constrain the blurry image, and the other is the generator model combining (UPR)-Blocks and D-Blocks. An (UPR)-Block is composed of one upsampling layer and 3 convolution layers. Consisting of an average-pooling layer and multiple convolution layers, a D-Block comes with different kernel sizes that capture global, and local spatial information of the raw image, separately. By analyzing the information of gradient, we obtain a TV-based based on minimum lower bound of loss function of the generator. Our experiments show that the proposed method outperforms the state-of-the-art conventional algorithms significantly.     

Local albedo-insensitive single image dehazing

In this paper, we present a new algorithm to remove haze from a single image. The proposed algorithm extracts transmission iteratively under the assumption that large-scale chromaticity variations are due to transmission while small-scale luminance variations are due to scene albedo. A nonlinear edge-preserving filter is introduced to incrementally refine subtle transmission map while still keeping sharp transmission map distinct. The algorithm is verified by both synthetic images and real-scene photographs. The results demonstrate that our method can produce transmission maps without being affected by the local albedo variations and, furthermore, recover haze-free images. On top of haze removal, several applications of the transmission map including refocusing and relighting are also implemented.     

正则化方法及非刚体匹配在医学动态图象分析中的应用

为了给医生利用医学图象进行诊断和分析心血管疾病提供一个有效的工具和途径，利用计算机视觉中的正则化方法，结合心脏和心血管动态特征的临床知识，对两种医学动态图象(超声心动图和心血管造影图)进行了定量的运动分析，并完成了一套应用软件．实验结果证明，该方法明显优于以往的图象分析方法。     

SEGMENTATION OF NATURAL IMAGES USING ANISOTROPIC DIFFUSION AND LINKING OF BOUNDARY EDGES

We present a segmentation method of natural images that uses an anisotropic diffusion algorithm and a region growing algorithm. We propose a modified version of the anisotropic diffusion algorithm as a precise edge-preserving smoothing technique modified by using boundary edges. We incorporate a linking algorithm for boundary edges based on a directional potential function into the anisotropic diffusion algorithm to improve the ability of edge-preserving smoothing. As a result, unnecessary details of images are effectively smoothed before performing a region growing algorithm. Therefore, the proposed method is suitable for an accurate segmentation of natural images. Several simulated examples are presented that demonstrate the effectiveness of the proposed technique.     

A Variational Approach to Remove Outliers and Impulse Noise

We consider signal and image restoration using convex cost-functions composed of a non-smooth data-fidelity term and a smooth regularization term. We provide a convergent method to minimize such cost-functions. In order to restore data corrupted with outliers and impulsive noise, we focus on cost-functions composed of an ?₁ data-fidelity term and an edge-preserving regularization term. The analysis of the minimizers of these cost-functions provides a natural justification of the method. It is shown that, because of the ?₁ data-fidelity, these minimizers involve an implicit detection of outliers. Uncorrupted (regular) data entries are fitted exactly while outliers are replaced by estimates determined by the regularization term, independently of the exact value of the outliers. The resultant method is accurate and stable, as demonstrated by the experiments. A crucial advantage over alternative filtering methods is the possibility to convey adequate priors about the restored signals and images, such as the presence of edges. Our variational method furnishes a new framework for the processing of data corrupted with outliers and different kinds of impulse noise.     

基于LLE的边缘保持图像平滑算法

现有全局优化算法都使用不同范数约束输出图像梯度来实现图像平滑,但会牺牲图像中的弱结构信息来达到较好的平滑性能,导致输出图像出现颜色失真和细节模糊的情况。针对上述问题,提出一种基于LLE的边缘保持图像平滑算法(edge preserving image smoothing algorithm based on LLE,Ep-LLE),引入局部线性嵌入(LLE)的思想作为优化函数的正则化项并采用L₂范数进行惩罚。该方法利用图像局部区域内像素存在的相互关系,通过约束局部相似以实现图像平滑任务。最后通过各个算法的实验对比验证,基于LLE的边缘保持图像平滑算法能在实现图像边缘保持平滑的同时,保留图像局部结构特征,并有效避免区域内颜色一致导致的边缘阶梯状现象,避免图像颜色失真。     

基于边缘保留分解和改进稀疏表示的医学图像融合

针对多模态医学图像融合中容易产生伪影且存在细节缺失的问题,提出一种利用多尺度边缘保留分解和稀疏表示的二尺度多模态医学图像融合方法框架。首先利用边缘保留滤波器对源图像进行多尺度分解,得到源图像的平滑层和细节层。然后,将改进的稀疏表示算法用于融合平滑层,并在此基础上提出一种基于图像块筛选的策略来构建过完备字典的数据集,再利用字典学习算法训练出一种联合字典,同时引入一种多范数的活跃度度量方法选择稀疏系数;细节层的融合则采用自适应加权局部区域能量的融合规则。最后将融合后的平滑层和细节层进行多尺度重构得到融合图像。针对三类不同成像模态的医学图像进行对比实验,结果表明,该方法较其他多尺度变换和稀疏表示的方法能够保留更多显著的边缘特征,对比度也有明显提升,在视觉效果和客观评价上都具有一定优势。     

改进的正则化模型在图像恢复中的应用

目的 由拟合项与正则项组成的海森矩阵,如果不具有特殊结构,其逆矩阵计算比较困难,为克服此缺点,提出一种海森矩阵可分块对角化的牛顿投影迭代算法。方法 首先,用L₂范数描述拟合项,用自变量是有界变差函数的复合函数刻画正则项,建立能量泛函正则化模型。其次,引入势函数,将正则化模型转化为增广能量泛函。再次,构造预条件矩阵,使得海森矩阵可分块对角化。最后,为防止牛顿投影迭代算法收敛到局部最优解,采用回溯线性搜索算法和改进的Barzilai-Borwein步长更新准则使得算法全局收敛。结果 针对图像去模糊正则化模型容易使边缘平滑和产生阶梯效应“两难”问题,提出一种新的正则化模型和牛顿投影迭代算法。仿真结果表明,“两难”问题通过本文算法得到了很好的解决。结论 与其他正则化图像去模糊模型相比,本文算法明显改善图像的质量,如有效地保护图像的边缘,抑制阶梯效应,相对偏差和误差较小,较高的峰值信噪比和结构相似测度。     

Inertial motion tracking using sensor saturation compensation with <Emphasis Type="Italic">l</Emphasis><Subscript>1</Subscript> norm regularization

A smoother is proposed for inertial sensor-based motion tracking, where the sensor saturation is compensated. The sensor saturation estimation term is added using l ₁ norm regularization techniques to the standard smoothing problem. The proposed algorithm is in the form of a quadratic optimization problem. Three slightly different methods are proposed, where the geometric models on sensor saturation are slightly different. Through simulation and experiments, it is shown that the proposed method effectively compensates the sensor saturation.     

基于复数小波变换的边缘保护融合算法

如何保护局部对比度信息是图像融合的关键问题,而图像边缘是基于人类视觉系统(HVS)最敏感的局部对比度信息.基于对偶树复数小波变换(DT-CWT),提出一种保护图像边缘信息的加权系数融合算法.对于低频部分,使用邻域熵极大值准则将系数添加到融合图像中;而对于高频部分,首先分别对各小波子图像进行边缘提取并对其特征增强,接下来使用边缘信息优先的加权系数融合策略进行特征信息融合.实验结果表明,同传统多分辨率图像融合方法相比,能得到更好的融合效果.     

Local Convergence of the Lavrentiev Method for the Cauchy Problem via a Carleman Inequality

The purpose is to perform a sharp analysis of the Lavrentiev method applied to the regularization of the ill-posed Cauchy problem, set in the Steklov-Poincaré variational framework. Global approximation results have been stated earlier that demonstrate that the Lavrentiev procedure yields a convergent strategy. However, no convergence rates are available unless a source condition is assumed on the exact Cauchy solution. We pursue here bounds on the approximation (bias) and the noise propagation (variance) errors away from the incomplete boundary where instabilities are located. The investigation relies on a Carleman inequality that enables enhanced local convergence rates for both bias and variance errors without any particular smoothness assumption on the exact solution. These improved results allows a new insight on the behavior of the Lavrentiev solution, look similar to those established for the Quasi-Reversibility method in [Inverse Problems 25, 035005, 2009]. There is a case for saying that this sort of ??super-convergence?? is rather inherent to the nature of the Cauchy problem and any reasonable regularization procedure would enjoy the same locally super-convergent behavior.     

Block-matching-based motion field generation utilizing directional edge displacement

A motion field generation algorithm using block matching of edge flag histograms has been developed aiming at its application to motion recognition systems. Use of edge flags instead of pixel intensities has made the algorithm robust against illumination changes. In order to detect local motions of interest effectively, a new adaptive frame interval adjustment scheme has been introduced in which only the edge flags due to local motions present in the frame are accumulated and utilized in block matching. These edge flags are projected onto x and y axes to generate histograms and the motion in x and y directions are determined by histogram matching. As a result, the computational cost for best match search has been substantially reduced. A vector representation of the motion field, which is called projected principal-motion distribution (PPMD), has also been proposed. It was applied to preliminary motion recognition experiments using Hidden Markov Models (HMMs) and its effectiveness has been confirmed. Moreover the advantage of the proposed motion field generation method over the simple optical flow as well as the conventional block matching method using pixel intensities has been demonstrated.     

融合IMU去除运动模糊的改进光流匹配算法

为进一步提高视觉SLAM中的光流匹配精度和速度,提出一种融合惯性测量单元（inertial measurement unit,IMU）去除运动模糊的改进光流匹配算法。该算法首先利用IMU运动信息计算的点扩散函数去除运动模糊,提高特征点匹配率;其次在LK（Lucas-Kanade）光流的基础上引入梯度误差,并使用图像梯度L1范数作为正则项模拟稀疏噪声,构建代价函数;然后利用IMU预测特征点位置作为该算法初始值,并加入BB（Barzilar-Borwein）步长改进原有的高斯牛顿算法,提高计算速度。实验表明,通过两帧之间比较,该算法的效率和精度均优于LK光流法;然后将该算法集成到VINS-Mono框架,在数据集EuRoC上结果显示,该算法提高了原有框架的定位精度和鲁棒性。     

小波域边缘保持规整化图像复原

图像复原是一个病态问题,一般需要通过规整化技术得到一个合适的解.规整化的难点在于抑制噪声的同时要保持图像的边缘等重要的图像信息.为了更有效地保持复原图像的边缘,提出了小波域边缘保持规整化泛函的一般形式,并给出了相应的求解方法.针对小波域图像复原方法可能产生的Gibbs效应,利用自然图像小波变换的水平（竖直）子带在水平（竖直）方向的连续性,通过额外的惩罚项加以解决.仿真实验结果说明了该方法的有效性.