三维重建中散乱点云的聚类筛选与网格重建

三维重建过程中获得的初始海量数据存在大量的噪声和孤立点,使得直接使用这些数据进行网格重建时,将会产生尖锐的凸出,导致重建效果不好,甚至是网格重建失败.针对以上问题,提出首先采用基于密度聚类的方法筛选三维点云,然后进行网格重建.实验表明本文算法获得了较好的网格重建效果.     

面向点云的三维物体识别方法综述

随着三维扫描技术的快速发展,获取各类场景的点云数据已经非常简单快捷;加之点云数据具备不受光照、阴影、纹理的影响等优势,基于点云的三维物体识别已成为计算机视觉领域的研究热点。首先,对近年来面向点云数据的三维物体识别方法进行归纳和总结;然后,对已有方法的优势及缺点进行分析;最后,指出点云物体识别中所面临的挑战及进一步的研究方向。     

Topology-Aware Surface Reconstruction for Point Clouds

We present an approach to incorporate topological priors in the reconstruction of a surface from a point scan. We base the reconstruction on basis functions which are optimized to provide a good fit to the point scan while satisfying predefined topological constraints. We optimize the parameters of a model to obtain a likelihood function over the reconstruction domain. The topological constraints are captured by persistence diagrams which are incorporated within the optimization algorithm to promote the correct topology. The result is a novel topology-aware technique which can (i) weed out topological noise from point scans, and (ii) capture certain nuanced properties of the underlying shape which could otherwise be lost while performing surface reconstruction. We show results reconstructing shapes with multiple potential topologies, compare to other classical surface construction techniques, and show the completion of real scan data.     

基于原始点云的三维目标检测算法

针对当前三维目标检测中存在的数据降采样难、特征提取不充分、感受野有限、候选包围盒回归质量不高等问题,基于3DSSD三维目标检测算法,提出了一种基于原始点云、单阶段、无锚框的三维目标检测算法RPV-SSD(random point voxel single stage object detector),该算法由随机体素采样层、3D稀疏卷积层、特征聚合层、候选点生成层、区域建议网络层共五个部分组成,主要通过聚合随机体素采样的关键点逐点特征、体素稀疏卷积特征、鸟瞰图特征,进而实现对物体类别、3D包围盒以及物体朝向的预测。在KITTI数据集上的实验表明,该算法整体表现良好,不仅能够命中真值标签中的目标并且回归较好的包围盒,还能够从物体的不完整点云推测出物体的类别及其完整形状,提高目标检测性能。     

三维物体表面重建方法的分析

介绍了目前三维物体表面重建技术的两种常用方案，并对这两种方案的优缺点进行了较为详细的分析与比较，最后给出了它们不同的适用范围。     

A Survey of Surface Reconstruction from Point Clouds

The area of surface reconstruction has seen substantial progress in the past two decades. The traditional problem addressed by surface reconstruction is to recover the digital representation of a physical shape that has been scanned, where the scanned data contain a wide variety of defects. While much of the earlier work has been focused on reconstructing a piece‐wise smooth representation of the original shape, recent work has taken on more specialized priors to address significantly challenging data imperfections, where the reconstruction can take on different representations—not necessarily the explicit geometry. We survey the field of surface reconstruction, and provide a categorization with respect to priors, data imperfections and reconstruction output. By considering a holistic view of surface reconstruction, we show a detailed characterization of the field, highlight similarities between diverse reconstruction techniques and provide directions for future work in surface reconstruction.     

基于Sparse ICP 的三维点云耳廓识别

提出一种新颖的三维耳廓识别方法,首先基于PCA 和SVD 分解对三维耳廓点云模 型进行归一化预处理,以统一数据库中所有耳廓点云模型的位置与姿态;然后基于Iannarelli 分 类系统提取三维耳廓的4 个局部特征区域,并利用Sparse ICP 算法对局部特征区域进行匹配;最 后根据局部特征区域中对应点间的距离判断耳廓之间的差异测度,实现耳廓形状识别。实验证明, 本文算法与其他算法相比具有较高的识别精度和识别效率。     

三维重建中点云模型与纹理图像的配准

研究三维立体图像优化问题,实现高真实度的纹理图.由于立体图像重建过程产生累加误差,影响匹配精度.目前半自动和自动纹理贴图中三维扫描数据与高分辨率纹理图像对应点配准精度低、计算量大.为解决上述问题,在标准ICP(Iterative Closest Point)算法的基础上,提出一种改进的LM-ICP 2D和3D配准算法.通过法向量内积加权的最近点迭代,动态更新特征对应,减小误匹配点对配准精度的影响,并利用LM(Levenberg-Marquardt)算法优化投影矩阵.采用真实数据进行仿真.实验表明,提出的算法能得到精度高、真实性强的匹配图像效果,为设计提供参考.     

基于3维点云鸟瞰图的高精度实时目标检测

针对基于3维点云的目标检测问题,提出了一种高精度实时的单阶段深度神经网络,分别在网络特征提取、损失函数设计和训练数据增强等3个方面提出了新的解决方案.首先对点云直接进行体素化来构建鸟瞰图.在特征提取阶段,使用残差结构提取高层语义特征,并融合多层次特征输出稠密的特征图.在回归鸟瞰图上的目标框的同时,在损失函数中考虑二次偏移量以实现更高精度的收敛.在网络训练中,使用不同帧3维点云混合的方式进行数据增强,提高网络的泛化性能.基于KITTI鸟瞰图目标检测数据集的实验结果表明,本文提出的网络仅使用雷达点云的位置信息,在性能上不仅优于目前最先进的鸟瞰图目标检测网络,而且优于融合图像和点云的检测方案,且整个网络运行速度达到20帧/秒,满足实时性要求.     

3D Surface Reconstruction Using Occluding Contours

This paper addresses the problem of 3D surface reconstruction using image sequences. It has been shown that shape recovery from three or more occluding contours of the surface is possible given a known camera motion. Several algorithms, which have been recently proposed, allow such a reconstruction under the assumption of a linear camera motion. A new approach is presented which deals with the reconstruction problem directly from a discrete point of view. First, a theoretical study of the epipolar correspondence between occluding contours is achieved. A correct depth formulation is then derived from a local approximation of the surface up to order two. This allows the local shape to be estimated, given three consecutive contours, without any constraints on the camera motion. Experimental results are presented for both synthetic and real data.     

平行点云: 虚实互动的点云生成与三维模型进化方法

三维信息的提取在自动驾驶等智能交通场景中正发挥着越来越重要的作用, 为了解决以激光雷达为主的深度传感器在数据采集方面面临的成本高、样本覆盖不全面等问题, 本文提出了平行点云的框架. 利用人工定义场景获取虚拟点云数据, 通过计算实验训练三维模型, 借助平行执行对模型性能进行测试, 并将结果反馈至数据生成和模型训练过程. 通过不断地迭代, 使三维模型得到充分评估并不断进化. 在平行点云的框架下, 我们以三维目标检测为例, 通过闭环迭代, 构建了虚实结合的点云数据集, 在无需人工标注的情况下, 可达到标注数据训练模型精度的72%.     

基于自适应权值的点云三维物体重建算法研究

基于三维扫描点云数据的三维物体重建是计算机图形学中非常重要的课题,在计 算机动画、医学图像处理等多方面都有应用。其中基于最小二乘问题的Levenberg-Marquart 算 法和基于极大似然估计的M-Estimator 算法都是不错的方案。但是当点的数量过多过少或者点 云中有噪声时,这些方案产生的结果都会有较大的误差,影响重建的效果。为了解决这两个问 题,结合Levenberg-Marquart 算法和M-Estimator 算法,提出了一种新的算法。该算法结合 Levenberg-Marquart 算法较快的收敛性和M-Estimator 算法的抗噪性,能很好地解决点数量较多 和噪声点影响结果的问题。通过在M-Estimator 的权重函数上进行改进,提出自适应的权值函 数,用灵活变动和自适应的值代替原来的固定值,使算法在噪声等级较高时也能表现良好。最 后将算法应用在球体和圆柱上,并和最新的研究成果进行对比,数据说明算法无论是在点云数 量较多还是在噪声等级较高的情况下都明显优于其他已知算法。     

基于深度学习的物体点云六维位姿估计方法

物体位姿估计是机器人在散乱环境中实现三维物体拾取的关键技术,然而目前多数用于物体位姿估计的深度学习方法严重依赖场景的RGB信息,从而限制了其应用范围.提出基于深度学习的六维位姿估计方法,在物理仿真环境下生成针对工业零件的数据集,将三维点云映射到二维平面生成深度特征图和法线特征图,并使用特征融合网络对散乱场景中的工业零件...     

VASE: Volume‐Aware Surface Evolution for Surface Reconstruction from Incomplete Point Clouds

Objects with many concavities are difficult to acquire using laser scanners. The highly concave areas are hard to access by a scanner due to occlusions by other components of the object. The resulting point scan typically suffers from large amounts of missing data. Methods that use surface‐based priors rely on local surface estimates and perform well only when filling small holes. When the holes become large, the reconstruction problem becomes severely under‐constrained, which necessitates the use of additional reconstruction priors. In this paper, we introduce weak volumetric priors which assume that the volume of a shape varies smoothly and that each point cloud sample is visible from outside the shape. Specifically, the union of view‐rays given by the scanner implicitly carves the exterior volume, while volumetric smoothness regularizes the internal volume. We incorporate these priors into a surface evolution framework where a new energy term defined by volumetric smoothness is introduced to handle large amount of missing data. We demonstrate the effectiveness of our method on objects exhibiting deep concavities, and show its general applicability over a broader spectrum of geometric scenario.     

面向PET图像重建的结构先验导引的自适应点云方法

正电子发射断层成像(PET)重建的核心是解决重建精度和重建速度的问题.针对传统重建方法中以PET符合计数值表达待求图像的每个点像素值的规则点表达框架的问题,提出利用结构先验导引的自适应点云表达待求图像的点云表达框架的方法,从而可在保证重建精度的条件下有效地提高重建速度.该方法采用两步布点的方法引入点云表达框架:第一步基...     

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.     

组件感知的高分辨率三维物体重建方法

基于体素表示的三维物体重建计算代价会随着体素分辨率的增加呈立方增长.为了缓解这一问题,提出组件感知的三维物体重建方法,将三维物体分解成多个组件,通过预测组件几何结构和组装组件的方式重建三维物体,从而将高分辨率三维物体的重建问题分解成一系列低分辨率组件的重建问题.组件感知的三维物体重建方法使用组件位置预测模块预测所有组件的位置;使用组件特征提取模块融合组件表观特征与组件几何特征生成组件联合特征;使用组件几何结构重建模块根据组件联合特征重建组件的几何形状;最后将所有组件按其位置信息组装成高分辨率的三维物体.实验使用ShapeNet数据集在一个拥有12 GB内存的NVIDIA 1080 Maxwell GPU上进行.对比方法包括一个基于八叉树的高分辨率重建方法、一个基于LSTM的低分辨率重建方法和一个使用编码器-解码器架构的Baseline方法.高分辨率重建结果显示,组件感知的三维物体重建方法能够以较小的计算代价取得满意的高分辨率三维物体重建精度.在低分辨率重建实验上,该方法也取得了更高的重建精度,在13个类别上的平均精度达到了0.618.     

Indoor Scene Reconstruction from Sets of Noisy Range Images

This paper describes a system for building 3D models of indoor scenes from sets of noisy laser range images. It addresses several important aspects of this problem, namely, preprocessing, which includes image segmentation and planar model fitting; view registration, which is the method of determining the rigid transformation that describes the relative pose of the camera platform between views; and reconstruction, which is the subsequent integration or fusion of separate range images into a single 3D model. Our proposed strategy is to use a statistical sensor model. We thus account for noise properties of the data at each stage in the reconstruction process, which produces reliable results even in the presence of significant measurement noise. We give an empirical analysis of a plane-based registration method and present results using real range data that demonstrate the performance of the entire reconstruction system.     

3D Surface Reconstruction Using a Generalized Distance Function

We define a generalized distance function on an unoriented 3D point set and describe how it may be used to reconstruct a surface approximating these points. This distance function is shown to be a Mahalanobis distance in a higher‐dimensional embedding space of the points, and the resulting reconstruction algorithm a natural extension of the classical Radial Basis Function (RBF) approach. Experimental results show the superiority of our reconstruction algorithm to RBF and other methods in a variety of practical scenarios.