A 3D Model Reconstruction Method Based on Mesh Deformation

Abstract

The present invention proposes a three-dimensional model reconstruction method based on grid deformation to construct a training sample set, including making discrete perspective pictures of multiple models and corresponding three-dimensional point cloud data; setting a deep learning network model based on a graph convolutional neural network , the deep learning network model based on the graph convolutional neural network includes a discrete perspective feature fusion module and a grid deformation module, the output connection of the discrete perspective feature fusion module is connected to the input of the grid deformation module; a loss function is set, based on training The sample set is used to train the deep learning network model based on the graph convolutional neural network; input the discrete perspective pictures of the object to be reconstructed into the trained network model, and automatically reconstruct the 3D mesh model and evaluate the accuracy. This method can support stable and accurate automatic 3D mesh model reconstruction for objects of different types and sizes by learning and training discrete perspective images and 3D point cloud data sets of objects.

Description

technical field [0001] The invention belongs to the field of three-dimensional reconstruction, in particular to a three-dimensional model reconstruction method based on grid deformation. Background technique [0002] 3D reconstruction is an extremely challenging problem that has been studied in the field of computer vision for decades. Traditional methods based on multi-view geometry, such as many SFM and SLAM algorithms, involve a series of complex processes, including feature extraction, feature matching, matching point triangulation, etc. Therefore, this method is not robust to challenging scenarios where feature extraction or matching cannot be done efficiently. Furthermore, their 3D reconstruction result is usually a sparse reconstruction that cannot be used directly. To overcome these limitations, several learning-based methods have emerged. Using deep visual image features, depth regression estimation is performed on the scene to obtain dense reconstruction results...

AI Technical Summary

Problems solved by technology

This kind of inferring the 3D model of an object from only one RGB image is undoubtedly very attractive, but the above methods are inherently limited by a single view

Because the geometric prior obtained from an image from only one angle is often too limited to accurately reconstruct the geometry of objects not seen in this image

Images