A three-dimensional point cloud model training method for three-dimensional model construction

Abstract

The invention provides a three-dimensional point cloud model training method and device for three-dimensional model construction. The method comprises the following steps of obtaining a set of training, dividing each group of three-dimensional point cloud data in the training set into a first set and a second set, inputting the point data in the first set into a preset three-dimensional point cloud model to obtain a first prediction set, inputting the prediction point data in the first prediction set into the same model to obtain a second prediction set, obtaining a first loss function valueaccording to a preset first loss function, obtaining a second loss function value according to a preset second loss function, calculating the first loss function value and the second loss function value to obtain a third loss function value corresponding to each group of point cloud data, and training a preset three-dimensional point cloud model according to the plurality of third loss function values corresponding to the plurality of groups of three-dimensional point cloud data, so as to construct the three-dimensional model according to the trained preset three-dimensional point cloud model.Therefore, the trained preset three-dimensional point cloud model improves the point cloud data feature learning effect.

Description

technical field [0001] The present application relates to the technical field of computer vision and machine learning, in particular to a 3D point cloud model training method for 3D model construction. Background technique [0002] 3D point cloud data is gradually increasing with the development of deep scanning equipment. Compared with the flat space of two-dimensional images, three-dimensional point cloud data contains more spatial structure information, and its irregular structure and spatial transformability make analysis more difficult, requiring a more comprehensive approach Further processing and understanding of 3D point cloud spatial information. [0003] As deep learning has made breakthroughs in many visual analysis fields, many scholars have used deep learning methods to process and extract features from 3D point clouds. The first deep learning methods to deal with 3D point clouds are methods based on supervised learning, such as PointNet and PointNet++. Howev...

AI Technical Summary

Problems solved by technology

[0006] For this reason, this application proposes a 3D point cloud model training method for 3D model construction to solve the problem of calculating the loss function by calculating the distance between the predicted point data and the target point data in the prior art, resulting in 3D point cloud The technical problem of the overfitting phenomenon in the points generated by the cloud model

Images