Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Three-dimensional point cloud restoration method based on local smoothness and non-local similarity

A technology of three-dimensional point cloud and repair method, which is applied in the field of point cloud repair, and can solve the problems that the boundary is prone to artifacts and distortion.

Active Publication Date: 2019-06-07
PEKING UNIV
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of method completely relies on the local information around the hole to repair. Since the reference information is relatively simple, the repair result is more flat than the actual content, which is easy to be distorted, and when the geometric structure is complex, the repaired boundary is prone to artifacts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Three-dimensional point cloud restoration method based on local smoothness and non-local similarity
  • Three-dimensional point cloud restoration method based on local smoothness and non-local similarity
  • Three-dimensional point cloud restoration method based on local smoothness and non-local similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041]In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

[0042] Aiming at the method of the present invention, firstly introduce the basic concepts in the spectral graph theory, and then propose the eigenvector frequency interpretation based on the graph node domain, the spectral graph theory will be the core of the method in the invention. The spectrum theory includes the following contents:

[0043] (1) Graph and graph Laplacian operator:

[0044] Define an undirected graph, G={V,E,W}. V is the set of vertices on the graph, |V|=N; E is the set of edges; W is the weighted adjacency matrix. where W is a N×N real symmetric matrix, w i,j is the weight of the edge connecting vertex i to vertex j, and usually uses a non-negative value as the weight.

[0045] The graph Laplacian is usually defined as L=D-W, where D i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a three-dimensional point cloud restoration method based on local smoothness and non-local similarity, and relates to the field of graph signal processing, and the method comprises the main steps: voxelization of point cloud, detection of point cloud holes, search of similar areas, matching of relative positions, and restoration of missing areas. According to the method, thecomplex geometric structure can be well repaired, the loss of the geometric structure is reduced, artifacts are not generated, and the repair fidelity is high.

Description

technical field [0001] The invention relates to the field of point cloud restoration, and its theoretical basis relates to the field of image signal processing, in particular to a three-dimensional point cloud restoration method based on local smoothness and non-local similarity. Background technique [0002] Point cloud data collected by 3D scanners and depth sensing will inevitably produce data errors: for some areas that cannot be scanned, they will be presented in the form of holes with missing data in the scanning results. Reasons for missing data include incomplete scanning angles, limitations of laser scanners, and complex geometric structures of objects. [0003] In terms of hole detection, there are currently two mainstream algorithms: grid-based methods and point-based methods. [0004] The grid-based method is mainly to construct a grid on the point cloud. Emelyanov et al., Orriols et al., and Floater et al. extract hole boundaries through some greedy strategies,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T17/20
Inventor 胡玮傅泽卿郭宗明
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com