A GPU-Based Framework for Generating Implicit Datasets of Voxelized Polygonal Models for the Training of 3D Convolutional Neural Networks

IEEE Access vol. 8 pp. 12675-1268

Carlos-Javier Ogayar-Anguita; Antonio-Jesús Rueda-Ruiz; Rafael-Jesús Segura-Sánchez; Miguel Díaz-Medina; Ángel-Luis García-Fernández

Abstract

In this paper we present an efficient GPU-based framework to dynamically perform the voxelization of polygonal models for training 3D convolutional neural networks. It is designed to manage the dataset augmentation by using efficient geometric transformations and random vertex displacements in GPU. With the proposed system, every voxelization is carried out on-the-fly for directly feeding the network. The computing performance with this approach is much better than with the standard method, that carries out every voxelization of each model separately and has much higher data processing overhead. The core voxelization algorithm works by using the standard rendering pipeline of the GPU. It generates binary voxels for both the interior and the surface of the models. Moreover, it is simple, concise and very compatible with commodity hardware, as it neither uses complex data structures nor needs vendor-specific hardware or additional dependencies. This framework dramatically reduces the input/output operations, and completely eliminates the storage footprint of the voxelization dataset, managing it as an implicit dataset.

DOI: 10.1109/ACCESS.2020.2965624

BibTeX

@article{Ogayar2020,
	author = {Carlos Javier Ogayar-Anguita and Antonio Jes\'us Rueda-Ruiz and Rafael Jes\'us Segura-S\'anchez and Miguel D\'iaz-Medina and \'Angel Luis Garc\'ia-Fern\'andez},
	title = {A GPU-Based Framework for Generating Implicit Datasets of Voxelized Polygonal Models for the Training of 3D Convolutional Neural Networks},
	journal = {IEEE Access},
	pages = {12675-1268},
	volume = {8},
	year = {2020},
	doi = {10.1109/ACCESS.2020.2965624},
	issn = {2169-3536}
}