Laser point cloud super-resolution reconstruction method based on self-attention generative adversarial network

Abstract

The invention discloses a laser point cloud super-resolution reconstruction method based on a self-attention generative adversarial network, and the method comprises the steps of carrying out the feature extraction of a laser point cloud image in a generator network, and obtaining the laser point cloud features; carrying out feature expansion on the laser point cloud features, and then carrying out coordinate reconstruction to obtain dense point cloud data; identifying the dense point cloud data to determine a corresponding confidence coefficient; pre-judging the corresponding dense point cloud data according to the confidence coefficient of the dense point cloud data, if the confidence coefficient value is close to 1, predicting that the input is possibly from target distribution with high confidence coefficient by the discriminator, otherwise, performing feature integration on the dense point cloud data by a generator to obtain an output feature; and training the adversarial networkthrough the output features to obtain final dense point cloud data. According to the invention, feature information sharing among different feature extraction units can be realized, the size of the model is reduced while the reconstruction precision is improved, and lightweight of the network model is facilitated.

Description

technical field [0001] The invention belongs to the field of laser point cloud data super-resolution, and in particular relates to a laser point cloud super-resolution reconstruction method based on self-attention generation confrontation network. Background technique [0002] With the continuous development of unmanned driving technology, algorithms such as 3D data display, 3D effect rendering, 3D target segmentation, detection and recognition based on laser 3D point cloud data have received more and more attention in recent years. However, the original 3D point cloud data collected by general lidar has shortcomings such as sparse distribution, poor uniformity, and obvious noise. The above shortcomings are also reflected in widely used public benchmark datasets such as KITTI and ScanNet. Therefore, before the subsequent processing and analysis of the original 3D point cloud data, it is necessary to preprocess it to improve the quality of the original point cloud data and pr...

AI Technical Summary

Problems solved by technology

However, this is a challenge for 3D point clouds because, unlike images, point cloud data is unstructured and irregular, and point clouds are usually the result of customer-grade scanning devices, which are often sparse, noisy and incomplete

Therefore, upsampling technology is particularly important, but the adaptation of image space technology to point sets is not simple

Images