scholarly journals Self-Sampling for Neural Point Cloud Consolidation

2021 ◽  
Vol 40 (5) ◽  
pp. 1-14
Author(s):  
Gal Metzer ◽  
Rana Hanocka ◽  
Raja Giryes ◽  
Daniel Cohen-Or
Keyword(s):  
Point Cloud ◽  
Sampling Methods ◽  
Difficult Problem ◽  
Local Statistics ◽  
Novel Technique ◽  
Input Point ◽  
Shape Learning ◽  
Fixed Set ◽  
Point Set ◽  
Non Local

We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. Unlike other point up-sampling methods which analyze shapes via local patches, in this work, we learn from global subsets. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. Specifically, we define source and target subsets according to the desired consolidation criteria (e.g., generating sharp points or points in sparse regions). The network learns a mapping from source to target subsets, and implicitly learns to consolidate the point cloud. During inference, the network is fed with random subsets of points from the input, which it displaces to synthesize a consolidated point set. We leverage the inductive bias of neural networks to eliminate noise and outliers, a notoriously difficult problem in point cloud consolidation. The shared weights of the network are optimized over the entire shape, learning non-local statistics and exploiting the recurrence of local-scale geometries. Specifically, the network encodes the distribution of the underlying shape surface within a fixed set of local kernels, which results in the best explanation of the underlying shape surface. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.

Non-local Low-rank Point Cloud Denoising for 3D Measurement Surfaces

2022 ◽  
pp. 1-1
Author(s):  
Dingkun Zhu ◽  
Honghua Chen ◽  
Weiming Wang ◽  
Haoran Xie ◽  
Gary Cheng ◽  
...  
Keyword(s):  
Point Cloud ◽  
Low Rank ◽  
3D Measurement ◽  
Non Local

Computation of Discrete Medial Axis Using Local Search in Domain Delaunay Triangulation of a Solid

2020 ◽  
Vol 21 (2) ◽  
Author(s):  
G. K. Sharma ◽  
B. Gurumoorthy
Keyword(s):  
Local Search ◽  
Point Cloud ◽  
Medial Axis ◽  
Medial Axis Transform ◽  
Surface Mesh ◽  
Sampling Density ◽  
Input Point ◽  
Topological Features ◽  
Definition Of ◽  
The Given

Abstract A new method is proposed to determine the points on the medial axis transform (MAT) of an object from its surface mesh representation. Current art typically uses a Voronoi diagram-based approach to generate the medial axis of a given point cloud on the boundary of the object or a surface mesh representation as input. This approach defines the MAT points as a subset of the Voronoi vertices close to the medial axis, where the accuracy and density of the points on the medial axis depend on the sampling density of the input point cloud representation. Therefore, the set of medial axis points is incomplete and may lack various topological features of the MAT and its reconstruction property. Instead of filtering the Voronoi vertices that are not medial points, the method proposed in this paper searches for the correct MAT point in the vicinity of such Voronoi vertices and finds the pair of corresponding footpoints using the properties of the MAT point. Hence, the algorithm can determine points on the medial axis without being dependent on the given sampling density and even in the presence of inputs having non-manifold entities. As the MAT points are generated based on the definition of medial axis (MA), the result obtained is accurate to within a specified tolerance.

Construction of Point Set Surfaces through Quadric Polynomials

2014 ◽  
Vol 565 ◽  
pp. 253-259
Author(s):  
Yu Liu
Keyword(s):  
Vector Field ◽  
Energy Function ◽  
Field Experiments ◽  
Point Clouds ◽  
Weighted Sum ◽  
Input Point ◽  
Point Set ◽  
Point Set Surfaces ◽  
Normal Vectors ◽  
Sum Of Distances

This paper constructs PSSs (Point Set Surfaces) by combining locally fitted quadric polynomials. First, an energy function is defined as the weighted sum of distances from a point to these quadric polynomials. Then, a vector field is constructed by the weighted sum of normal vectors at input points. Finally, points on a PSS are obtained by finding local minima of the energy function along the vector field. Experiments demonstrate that high quality PSSs can be obtained from the method presented for input point clouds sampled from various shapes.

Adaptive Slicing of Moving Least Squares Surfaces: Toward Direct Manufacturing of Point Set Surfaces

2007 ◽  
Author(s):  
Pinghai Yang ◽  
Xiaoping Qian
Keyword(s):  
Least Squares ◽  
Point Cloud ◽  
Moving Least Squares ◽  
Point Sets ◽  
New Approach ◽  
Adaptive Slicing ◽  
3D Sensing ◽  
Point Set ◽  
Point Set Surfaces ◽  
Model Conversion

Rapid advancement of 3D sensing techniques has lead to dense and accurate point cloud of an object to be readily available. The growing use of such scanned point sets in product design, analysis and manufacturing necessitates research on direct processing of point set surfaces. In this paper, we present an approach that enables the direct layered manufacturing of point set surfaces. This new approach is based on adaptive slicing of moving least squares (MLS) surfaces. Salient features of this new approach include: 1) it bypasses the laborious surface reconstruction and avoids model conversion induced accuracy loss; 2) the resulting layer thickness and layer contours are adaptive to local curvature and thus it leads to better surface quality and more efficient fabrication; 3) the MLS surface naturally smoothes the point cloud and allows up-sampling and down-sampling, and thus it is robust even for noisy or sparse point sets. Experimental results of the slicing algorithm on both synthetic and scanned point sets are presented.

scholarly journals Local statistics and non-local mean filter for speckle noise reduction in medical ultrasound image

2016 ◽  
Vol 195 ◽  
pp. 88-95 ◽  
Author(s):  
Jian Yang ◽  
Jingfan Fan ◽  
Danni Ai ◽  
Xuehu Wang ◽  
Yongchang Zheng ◽  
...  
Keyword(s):  
Noise Reduction ◽  
Ultrasound Image ◽  
Speckle Noise ◽  
Medical Ultrasound ◽  
Local Statistics ◽  
Mean Filter ◽  
Local Mean ◽  
Non Local ◽  
Speckle Noise Reduction

scholarly journals REVERSE NEAREST NEIGHBOR QUERIES IN FIXED DIMENSION

2011 ◽  
Vol 21 (02) ◽  
pp. 179-188 ◽  
Author(s):  
OTFRIED CHEONG ◽  
ANTOINE VIGNERON ◽  
JUYOUNG YON
Keyword(s):  
Data Structure ◽  
Nearest Neighbor ◽  
Dimensional Euclidean Space ◽  
Query Point ◽  
Reverse Nearest Neighbor ◽  
Input Point ◽  
Fixed Dimension ◽  
Nearest Point ◽  
Point Set ◽  
Nearest Neighbor Queries

Reverse nearest neighbor queries are defined as follows: Given an input point set P, and a query point q, find all the points p in P whose nearest point in P ∪ {q} \ {p} is q. We give a data structure to answer reverse nearest neighbor queries in fixed-dimensional Euclidean space. Our data structure uses O(n) space, its preprocessing time is O(n log n), and its query time is O( log n).

scholarly journals Ground Segmentation Algorithm of Lidar Point Cloud Based on Ray-Ransac

2021 ◽  
Vol 15 ◽  
pp. 970-977
Author(s):  
Yawei Zhao ◽  
Yanju Liu ◽  
Yang Yu ◽  
Jiawei Zhou
Keyword(s):  
Point Cloud ◽  
Structural Characteristics ◽  
Segmentation Algorithm ◽  
Model Parameters ◽  
Good Precision ◽  
Seed Point ◽  
Original Seed ◽  
Ground Segmentation ◽  
Point Set ◽  
Ransac Algorithm

Aiming at the problems of poor segmentation effect, low efficiency and poor robustness of the Ransac ground segmentation algorithm, this paper proposes a radar segmentation algorithm based on Ray-Ransac. This algorithm combines the structural characteristics of three-dimensional lidar and uses ray segmentation to generate the original seed point set. The random sampling of Ransac algorithm is limited to the original seed point set, which reduces the probability that Ransac algorithm extracts outliers and reduces the calculation. The Ransac algorithm is used to modify the ground model parameters so that the algorithm can adapt to the undulating roads. The standard deviation of the distance from the point to the plane model is used as the distance threshold, and the allowable error range of the actual point cloud data is considered to effectively eliminate the abnormal points and error points. The algorithm was tested on the simulation platform and the test vehicle. The experimental results show that the lidar point cloud ground segmentation algorithm proposed in this paper takes an average of 5.784 milliseconds per frame, which has fast speed and good precision. It can adapt to uneven road surface and has high robustness.

scholarly journals ROBUST AND ACCURATE PLANE SEGMENTATION FROM POINT CLOUDS OF STRUCTURED SCENES

2020 ◽  
Vol V-2-2020 ◽  
pp. 221-226
Author(s):  
P. Hu ◽  
Y. Liu ◽  
M. Tian ◽  
M. Hou
Keyword(s):  
Energy Minimization ◽  
Point Cloud ◽  
Point Clouds ◽  
Segmentation Method ◽  
Topological Graph ◽  
New Approach ◽  
Input Point ◽  
Planar Surfaces ◽  
Point Density ◽  
Efficiency And Effectiveness

Abstract. Plane segmentation from the point cloud is an important step in various types of geo-information related to human activities. In this paper, we present a new approach to accurate segment planar primitives simultaneously by transforming it into the best matching issue between the over-segmented super-voxels and the 3D plane models. The super-voxels and its adjacent topological graph are firstly derived from the input point cloud as over-segmented small patches. Such initial 3D plane models are then enriched by fitting centroids of randomly sampled super-voxels, and translating these grouped planar super-voxels by structured scene prior (e.g. orthogonality, parallelism), while the generated adjacent graph will be updated along with planar clustering. To achieve the final super-voxels to planes assignment problem, an energy minimization framework is constructed using the productions of candidate planes, initial super-voxels, and the improved adjacent graph, and optimized to segment multiple consistent planar surfaces in the scenes simultaneously. The proposed algorithms are implemented, and three types of point clouds differing in feature characteristics (e.g. point density, complexity) are mainly tested to validate the efficiency and effectiveness of our segmentation method.

scholarly journals Fractional Super-Resolution of Voxelized Point Clouds

2021 ◽  
Author(s):  
Ricardo de Queiroz ◽  
DIOGO GARCIA ◽  
Tomas Borges
Keyword(s):  
Point Cloud ◽  
Super Resolution ◽  
Point Clouds ◽  
Test Results ◽  
Input Point ◽  
Extensive Test ◽  
Self Similar ◽  
Fractional Factor

<div>We present a method to super-resolve voxelized point clouds down-sampled by a fractional factor, using look-up-tables (LUT) constructed from self-similarities from its own down-sampled neighborhoods. Given a down-sampled point cloud geometry Vd, and its corresponding fractional down-sampling factor s, the proposed method determines the set of positions that may have generated Vd, and estimates which of these positions were indeed occupied (super-resolution). Assuming that the geometry of a point cloud is approximately self-similar at different scales, LUTs relating down-sampled neighborhood configurations with children occupancy configurations can be estimated by further down-sampling the input point cloud to Vd2 , and by taking into account the irregular children distribution derived from fractional down-sampling. For completeness, we also interpolate texture by averaging colors from adjacent neighbors. We present extensive test results over different point clouds, showing the effectiveness of the proposed method against baseline methods.</div>

Sign in / Sign up

Export Citation Format

Share Document