A Point Cloud Upsampling Method Based on Deep Learning

Abstract

The present invention discloses a point cloud upsampling method based on deep learning, comprising: obtaining training data composed of a first number of sparse input points and a second number of dense input points; constructing a deep network model for The initial eigenvectors extracted from a number of sparse input points are respectively copied and subjected to curvature-based sampling operations to obtain a second number of intermediate eigenvectors, and the splicing operation is performed on each intermediate eigenvector, and the intermediate eigenvectors after the splicing operation are input into multiple The layer perceptron determines the sampling prediction point based on the sampling feature vector output by the multi-layer perceptron; trains the deep network model until the objective function determined by the sampling prediction point and dense input points converges; tests the deep network model to obtain the The sampled point cloud data. This method can transform the sparse point cloud into a dense point cloud based on the curvature adaptive distribution, which accurately characterizes the outline of the object, and is more conducive to the expression, rendering and visualization of 3D data.

Description

[0001] technology neighborhood [0002] The invention relates to the field of computer vision technology, in particular to a point cloud upsampling method based on deep learning. Background technique [0003] With the popularity of depth cameras and lidar sensors, point clouds, as a simple and efficient representation of 3D data, have gradually attracted widespread attention from researchers. In recent years, researchers have used end-to-end neural networks to directly process raw point cloud data, and have made qualitative breakthroughs in vision tasks based on point cloud representations (eg, 3D object recognition and detection, 3D scene segmentation, etc.). However, the original point cloud data is usually generated by consumer-level scanning equipment, which has problems such as sparsity, incompleteness, and noise interference, which brings a huge challenge to point cloud semantic analysis. Therefore, in order to be used more efficiently for rendering, analysis or other p...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem of being unable to accurately characterize the contour shape of objects existing in related technologies, the present invention provides a point cloud upsampling method based on deep learning

Images