Signing the Unsigned: Robust Surface Reconstruction from Raw Pointsets

We propose a modular framework for robust 3D reconstruction from unorganized, unoriented, noisy, and outlierridden geometric data. We gain robustness and scalability over previous methods through an unsigned distance approximation to the input data followed by a global stochastic signing of the function. An isosurface reconstruction is finally deduced via a sparse linear solve. We show with experiments on large, raw, geometric datasets that this approach is scalable while robust to noise, outliers, and holes. The modularity of our approach facilitates customization of the pipeline components to exploit specific idiosyncracies of datasets, while the simplicity of each component leads to a straightforward implementation.     

Error-guided adaptive Fourier-based surface reconstruction

In this paper, we propose to combine Kazhdan’s FFT-based approach to surface reconstruction from oriented points with adaptive subdivision and partition of unity blending techniques. This removes the main drawback of the FFT-based approach which is a high memory consumption for geometrically complex datasets. This allows us to achieve a higher reconstruction accuracy compared with the original global approach. Furthermore, our reconstruction process is guided by a global error control accomplished by computing the Hausdorff distance of selected input samples to intermediate reconstructions. The advantages of our surface reconstruction method also include a more robust surface restoration in regions where the surface folds back to itself.     

Feature‐Preserving Surface Reconstruction From Unoriented,Noisy Point Data

We propose a robust method for surface mesh reconstruction from unorganized, unoriented, noisy and outlier‐ridden 3D point data. A kernel‐based scale estimator is introduced to estimate the scale of inliers of the input data. The best tangent planes are computed for all points based on mean shift clustering and adaptive scale sample consensus, followed by detecting and removing outliers. Subsequently, we estimate the normals for the remaining points and smooth the noise using a surface fitting and projection strategy. As a result, the outliers and noise are removed and filtered, while the original sharp features are well preserved. We then adopt an existing method to reconstruct surface meshes from the processed point data. To preserve sharp features of the generated meshes that are often blurred during reconstruction, we describe a two‐step approach to effectively recover original sharp features. A number of examples are presented to demonstrate the effectiveness and robustness of our method.     

基于广义Gibbs先验的低剂量X-CT优质重建研究

为获取低剂量条件下X-CT的优质重建,提出基于广义Gibbs先验的低剂量X-CT重建算法。新算法首先对投影数据进行统计建模,其后采用Bayesian最大后验估计方法,将投影数据中非局部的先验信息加诸于该数据的恢复中,达到抑制噪声的效果,最后仍采用经典的滤波反投影方法对恢复后的投影数据进行解释CT重建。文中将非局部先验称为广义Gibbs先验,其原因在于该先验具有传统Gibbs先验形式的同时,可以通过选择较大邻域和自适应的加权方式充分利用投影数据的全局信息进行数据恢复。通过与已有算法的对比实验,表明该文提出的基于广义Gibbs先验的低剂量X-CT重建算法在降低噪声效果和保持边缘方面具有较好的表现。     

Multi-level hermite variational interpolation and quasi-interpolation

Based on the Hermite variational implicit surface reconstruction presented in Pan et al. (Science in China Series F: Information Sciences 52(2):308–315, 2009), we propose a multi-level interpolation method to overcome the problems resulted from using compactly supported radial basis functions (CSRBFs). In addition, we present a multi-level quasi-interpolation method which directly uses normal vectors to construct non-zero constraints and avoids solving any linear system, a common step of variational surface reconstruction, and leads to a fast and stable surface reconstruction from scattered points. With adaptive support size, our approach is robust and can successfully reconstruct surfaces on non-uniform and noisy point sets. Moreover, as the computation of quasi-interpolation is independent for each point, it can be easily parallelized on multi-core CPUs.     

Continuous global optimization in surface reconstruction from an oriented point cloud

We introduce a continuous global optimization method to the field of surface reconstruction from discrete noisy cloud of points with weak information on orientation. The proposed method uses an energy functional combining flux-based data-fit measures and a regularization term. A continuous convex relaxation scheme assures the global minima of the geometric surface functional. The reconstructed surface is implicitly represented by the binary segmentation of vertices of a 3D uniform grid and a triangulated surface can be obtained by extracting an appropriate isosurface. Unlike the discrete graph-cut solution, the continuous global optimization entails advantages like memory requirements, reduction of metrication errors for geometric quantities, and allowing globally optimal surface reconstruction at higher grid resolutions. We demonstrate the performance of the proposed method on several oriented point clouds captured by laser scanners. Experimental results confirm that our approach is robust to noise, large holes and non-uniform sampling density under the condition of very coarse orientation information.     

Sparse representation for robust abnormality detection in crowded scenes

In crowded scenes, the extracted low-level features, such as optical flow or spatio-temporal interest point, are inevitably noisy and uncertainty. In this paper, we propose a fully unsupervised non-negative sparse coding based approach for abnormality event detection in crowded scenes, which is specifically tailored to cope with feature noisy and uncertainty. The abnormality of query sample is decided by the sparse reconstruction cost from an atomically learned event dictionary, which forms a sparse coding bases. In our algorithm, we formulate the task of dictionary learning as a non-negative matrix factorization (NMF) problem with a sparsity constraint. We take the robust Earth Mover's Distance (EMD), instead of traditional Euclidean distance, as distance metric reconstruction cost function. To reduce the computation complexity of EMD, an approximate EMD, namely wavelet EMD, is introduced and well combined into our approach, without losing performance. In addition, the combination of wavelet EMD with our approach guarantees the convexity of optimization in dictionary learning. To handle both local abnormality detection (LAD) and global abnormality detection, we adopt two different types of spatio-temporal basis. Experiments conducted on four public available datasets demonstrate the promising performance of our work against the state-of-the-art methods.     

PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds

Point clouds obtained with 3D scanners or by image-based reconstruction techniques are often corrupted with significant amount of noise and outliers. Traditional methods for point cloud denoising largely rely on local surface fitting (e.g. jets or MLS surfaces), local or non-local averaging or on statistical assumptions about the underlying noise model. In contrast, we develop a simple data-driven method for removing outliers and reducing noise in unordered point clouds. We base our approach on a deep learning architecture adapted from PCPNet, which was recently proposed for estimating local 3D shape properties in point clouds. Our method first classifies and discards outlier samples, and then estimates correction vectors that project noisy points onto the original clean surfaces. The approach is efficient and robust to varying amounts of noise and outliers, while being able to handle large densely sampled point clouds. In our extensive evaluation, both on synthetic and real data, we show an increased robustness to strong noise levels compared to various state-of-the-art methods, enabling accurate surface reconstruction from extremely noisy real data obtained by range scans. Finally, the simplicity and universality of our approach makes it very easy to integrate in any existing geometry processing pipeline. Both the code and pre-trained networks can be found on the project page ( https://github.com/mrakotosaon/pointcleannet ).     

基于自适应块组割先验的噪声图像超分辨率重建

要增强噪声图像的分辨率,传统的串联方式依次进行去噪与超分辨率重建两个步骤,但去噪算法去除噪声的同时也损失了部分细节信息,影响了后续超分辨率重建的质量.为了使低分辨率噪声图像中所有细节信息都能参与超分辨率重建,本文以非局部中心化稀疏表示（Nonlocally centralized sparse representation,NCSR）模型为基础,提出了基于自适应块组割（Patch-group-cuts,PGCuts）先验的噪声图像超分辨率重建方法,同时实现去噪和超分辨率重建功能.块组割先验基于新颖的三维邻域系统和块组模型,能够达到图像去噪、边缘平滑和边缘清晰等效果.重建时以边缘强度为参考对块组割先验进行自适应约束,由于块组割在平滑区域约束力较低,采用分区域融合的方式进一步抑制噪声.本文对合成的低分辨率噪声图像和真实的低分辨率噪声图像进行了重建实验,实验表明,基于自适应块组割先验的噪声图像超分辨率重建算法,在丰富细节的同时能抑制噪声的干扰,不但具有较高的峰值信噪比和结构相似度等客观评价值,而且在非光滑区域具有很好的主观重建效果.     

Mutual-manifold regularized robust fast latent LRR for subspace recovery and learning

In this paper, we propose a simple yet effective low-rank representation (LRR) and subspace recovery model called mutual-manifold regularized robust fast latent LRR. Our model improves the representation ability and robustness from twofold. Specifically, our model is built on the Frobenius norm-based fast latent LRR decomposing given data into a principal feature part, a salient feature part and a sparse error, but improves it clearly by designing mutual-manifold regularization to encode, preserve and propagate local information between coefficients and salient features. The mutual-manifold regularization is defined by using the coefficients as the adaptive reconstruction weights for salient features and constructing a Laplacian matrix over salient features for the coefficients. Thus, some important local topology structure information can be propagated between them, which can make the discovered subspace structures and features potentially more accurate for the data representations. Besides, our approach also considers to improve the robust properties of subspace recovery against noise and sparse errors in coefficients, which is realized by decomposing original coefficients matrix into an error-corrected part and a sparse error part fitting noise in coefficients, and the recovered coefficients are then used for robust subspace recovery. Experimental results on several public databases demonstrate that our method can outperform other related algorithms.

     

Implicit and Nonparametric Shape Reconstruction from Unorganized Data Using a Variational Level Set Method

In this paper we consider a fundamental visualization problem: shape reconstruction from an unorganized data set. A new minimal-surface-like model and its variational and partial differential equation (PDE) formulation are introduced. In our formulation only distance to the data set is used as our input. Moreover, the distance is computed with optimal speed using a new numerical PDE algorithm. The data set can include points, curves, and surface patches. Our model has a natural scaling in the nonlinear regularization that allows flexibility close to the data set while it also minimizes oscillations between data points. To find the final shape, we continuously deform an initial surface following the gradient flow of our energy functional. An offset (an exterior contour) of the distance function to the data set is used as our initial surface. We have developed a new and efficient algorithm to find this initial surface. We use the level set method in our numerical computation in order to capture the deformation of the initial surface and to find an implicit representation (using the signed distance function) of the final shape on a fixed rectangular grid. Our variational/PDE approach using the level set method allows us to handle complicated topologies and noisy or highly nonuniform data sets quite easily. The constructed shape is smoother than any piecewise linear reconstruction. Moreover, our approach is easily scalable for different resolutions and works in any number of space dimensions.     

最小能量约束与ARDP算法混合的病灶点云重建

针对传统面绘制方法随真实感的提升效率急剧下降,且交互性及灵敏度较差的问题,基于CT点云数据提出了一种肝脏病灶的表面重建方法。首先改进了点云数据的插值和自适应精简方法;然后提出将模型重构过程分为两部分,先通过最小能量约束和简化的MC算法由点云距离场快速创建粗糙的基底模型,接着提出一种线性最优化的ARDP算法用于自动计算点元投影向量,从而将当前模型表面节点直接映射至点云,通过交互式地确定迭代次数可按需逐步提高模型精确度,最终获取高质量模型,实现散乱点到平滑面的直接过渡。实验结果表明,利用该算法生成平均误差小于0.000 1的高精模型将大大缩短时间,且对不规则病灶模型有着良好的适应性。     

Range image reconstruction based on robust multiresolution estimation of surface parameters

This paper proposes two robust multiresolution estimation methods of surface parameters for range images. Based on the robust estimation of surface parameters, the proposed methods approximate a patch to a planar surface in the locally adaptive window. Selection of resolution is made pixelwise by comparing a locally computed homogeneity measure with the global threshold obtained by the distribution of the approximation error. The proposed multiresolution surface parameter estimation methods are applied to range image reconstruction and segmentation. Computer simulation results with noisy images contaminated by additive Gaussian noise and impulse noise show that the proposed multiresolution reconstruction methods preserve step and roof edges better than the conventional methods. Also the segmentation methods based on the estimated surface parameters are shown to be robust to noise.     

Piecewise‐Planar 3D Reconstruction with Edge and Corner Regularization

This paper presents a method for the 3D reconstruction of a piecewise‐planar surface from range images, typically laser scans with millions of points. The reconstructed surface is a watertight polygonal mesh that conforms to observations at a given scale in the visible planar parts of the scene, and that is plausible in hidden parts. We formulate surface reconstruction as a discrete optimization problem based on detected and hypothesized planes. One of our major contributions, besides a treatment of data anisotropy and novel surface hypotheses, is a regularization of the reconstructed surface w.r.t. the length of edges and the number of corners. Compared to classical area‐based regularization, it better captures surface complexity and is therefore better suited for man‐made environments, such as buildings. To handle the underlying higher‐order potentials, that are problematic for MRF optimizers, we formulate minimization as a sparse mixed‐integer linear programming problem and obtain an approximate solution using a simple relaxation. Experiments show that it is fast and reaches near‐optimal solutions.     

稀疏性正则化的图像泊松恢复模型及分裂Bregman迭代算法

生物医学、天文等成像系统通常会受到泊松噪声的干扰, 基于图像在过完备字典下的稀疏表示, 在贝叶斯最大后验概率估计框架下, 建立了针对泊松噪声的稀疏性正则化图像恢复凸变分模型, 采用负log的泊松似然函数作为数据保真项, 模型中非光滑的正则项约束图像表示系数的稀疏性, 并附加恢复图像的非负性约束. 进一步, 基于分裂Bregman方法, 提出了求解该模型的多步迭代快速算法, 通过引入辅助变量与Bregman距离, 可将原问题转化为两个简单子问题的迭代求解, 大幅度降低了计算复杂性. 实验结果验证了本文模型与数值算法的有效性.     

带噪声散乱数据的光滑曲面重构——变分水平集方法

带噪声散乱数据点的光滑曲面重构应用广泛,基于变分水平集方法提出一种求解该问题的新的能量模型,并由此能量得到一新的微分方程,该微分方程演化后得到的极限曲面即为要重构的光滑曲面.给出了一种快速建立初始曲面的方法,节约了重构时间;然后对该微分方程的初值问题运用水平集方法求解,其中的空间方向离散化采用本质无震荡或加权本质无震荡技术,时间方向采用具有高精度的TVD Runge-Kutta技术.提出一种变步长的TVDRunge-Kutta方法来重新初始化符号距离函数,保证了Runge-Kutta方法中每一欧拉步都满足迎风设计要求.实验结果表明,该方法高效且能产生良好的重建效果.     

基于CIM的偏差补偿稀疏NLMAD算法研究

为了解决输入信号受噪声干扰和输出观测噪声具有脉冲特征的稀疏系统辨识问题,提出一种基于CIM的偏差补偿NLMAD(Normalized least mean absolute deviation, NLMAD)算法。 利用NLMAD算法可有效抵御脉冲输出观测噪声的优势,首先应用无偏准则设计偏差补偿NLMAD算法来有效解决由于输入噪声导致的估计偏差问题。再次考虑到稀疏系统辨识问题,将CIM作为稀疏约束惩罚项引入到偏差补偿NLMAD算法提出了新的稀疏自适应滤波算法CIMBCNLMAD。将所提算法应用于输入和输出均含有噪声的稀疏系统辨识和回声干扰抵消场景中,实验表明CIMBCNLMAD算法的稳态性能优于其它自适应滤波算法,说明该方法具有强的鲁棒性且可应用于工程实践。     

噪声环境下基于蒲丰距离的依概率多峰优化算法

针对噪声环境下求解多个极值点的问题, 本文提出了噪声环境下基于蒲丰距离的依概率多峰优化算法(Probabilistic multimodal optimization algorithm based on the Button distance, PMB). 算法依据蒲丰投针原理提出噪声下的蒲丰距离和极值分辨度概念, 理论推导证明了二者与算法峰值检测率符合依概率关系. 在全局范围内依据蒲丰距离划分搜索空间, 可以使PMB算法保持较好的搜索多样性. 在局部范围内利用改进的斐波那契法进行探索, 减少了算法陷入噪声引起的局部最优的概率. 基于34个测试函数, 从依概率特性验证、寻优结果影响因素分析、多极值点寻优和多维函数寻优四个角度进行实验. 证明了蒲丰距离与算法的峰值检测率符合所推导的依概率关系. 对比噪声环境下的改进蝙蝠算法和粒子群算法, PMB算法在噪声环境中可以依定概率更精确地定位多峰函数的更多极值点, 从而证明了PMB算法原理的正确性和噪声条件下全局寻优的依概率性能, 具有理论意义和实用价值.     

基于相对变换的半监督分类算法

为了增强基于图的局部和全部一致性(LGC)半监督算法的处理稀疏和噪声数据的能力,提出了一种基于相对变换的LGC算法。该算法通过相对变换将原始数据空间转换到相对空间,在相对空间中噪声和孤立点远离正常点,稀疏的数据变得相对密集,从而可以提高算法的性能。仿真实验结果表明,基于相对变换的LGC算法有更强的处理稀疏和噪声数据的能力。