Grid denoising method based on neural network

Abstract

The invention discloses a grid denoising method based on a neural network. The method comprises the following steps: carrying out pre-filtering operation by adopting guided normal filtering with fixedparameters, extracting a two-neighborhood plane normal generation image matrix of a pre-filtered grid model, carrying out alignment operation for rigid transformation and image rotation by utilizingnormal tensor voting, constructing a data set and training a neural network; and in an operation denoising stage, inputting an image matrix generated after pre-filtering of the noisy grid into the trained network model, restoring a new normal direction as a guide normal direction by utilizing the rotation matrix, and updating the normal direction and vertex information to obtain a denoised grid model. According to the method, the neural network is applied to the denoising problem of the three-dimensional grid, and the surface normal is mapped into the image matrix, so that the grid denoising effect of highly maintaining features can be simply and efficiently achieved.

Description

technical field [0001] The invention belongs to the field of computer graphics and relates to a grid denoising method based on a neural network, which is especially suitable for processing noise and fuzzy features in the process of three-dimensional data collection. Background technique [0002] Triangular mesh is the basic representation model of geometric objects in the fields of computer graphics, computer vision and virtual reality. In the process of obtaining grid surface data, due to the influence of acquisition equipment, environment and other factors, the obtained grid surface inevitably has errors. Therefore, most mesh surfaces contain different degrees of noise, which not only cannot objectively reflect the real information in the data, but also affects subsequent processing and calculation. Therefore, the denoising of triangular mesh surfaces is very necessary to obtain high-quality mesh data. [0003] Early filter-based denoising schemes applied isotropic algor...

AI Technical Summary

Problems solved by technology

Even if the strong geometric characteristics of the mesh surface can be preserved by using techniques such as quadratic fitting, its disadvantage is that it will smooth out the subtle features of the mesh surface

An optimization-based denoising algorithm can recover the mesh that best matches the input and is defined by some a priori definition of the noise, the constraints of the underlying surface geometry, such as Gaussian noise or independent and identically distributed noise, whose denoising is automatic, but they Difficult to generalize to meshes with different noise patterns and geometric characteristics, because some assumptions may break in real scenes

Images