Equidistant and Uniform Data Augmentation for 3D Objects

Abstract

Data augmentation is commonly used to increase the size and diversity of the datasets in machine learning. It is of particular importance to evaluate the robustness of the existing machine learning methods. With progress in geometrical and 3D machine learning, many methods exist to augment a 3D object, from the generation of random orientations to exploring different perspectives of an object. In high-precision applications, the machine learning model must be robust with respect to the small perturbations of the input object. Therefore, there is a need for 3D data augmentation tools that consider the distribution of distance metrics between the original and augmented objects. Here we present Eurecon, the first 3D data augmentation approach with spatial control over the augmented samples. It generates objects uniformly distributed over a sphere with a user-defined radius, which is a distance with respect to the original object. Eurecon is applicable to both point cloud and polygon mesh representations of the 3D objects, as demonstrated on the ModelNet dataset. The method is particularly useful in assessing and improving the machine learning models' robustness with respect to the transformations of a small magnitude. We demonstrated the superior performance of a point cloud-based model (PointNet++) and a mesh-based model (MeshNet) when trained on datasets augmented with Eurecon, compared to non-augmented and randomly augmented models. Eurecon is computationally efficient, taking 0.1 seconds to generate 1, 000 samples of an object of 1, 000 3D points. Eurecon works with the most common 3D file formats including point cloud and polygon mesh formats.