Patent · US Active

Method for point cloud up-sampling based on deep learning

US11880959B2 · kind B2 · utility

0Cited by
2References
4Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 30, 2020
Grant dateJan 23, 2024
Priority date
Expiry dateNov 4, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2219/2016
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present invention discloses a method for point cloud up-sampling based on deep learning, including: obtaining training data including a first number of sparse input points and a second number of dense input points; constructing a deep network model to be used for respectively performing replication and sampling operation based on curvature on initial eigenvectors extracted from the first number of sparse input points to obtain a second number of intermediate eigenvectors, performing splicing operation on each intermediate eigenvector, inputting the spliced intermediate eigenvectors into a multilayer perceptron, and determining sampling prediction points based on the sampling eigenvectors output by the multilayer perceptron; training the deep network model until an objective function determined by the sampling prediction points and the dense input points converges; and testing the deep network model to obtain point cloud data of an object under test after up-sampling.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.