Welcome to the InfoSci Platform
Reference Hub1
Data Augmentation Using GANs for 3D Applications

Data Augmentation Using GANs for 3D Applications

Ioannis Maniadis, Vassilis Solachidis, Nicholas Vretos, Petros Daras
Copyright: © 2020 |Pages: 41
ISBN13: 9781522552949|ISBN10: 1522552944|ISBN13 Softcover: 9781799829966|EISBN13: 9781522552956
DOI: 10.4018/978-1-5225-5294-9.ch011
Cite Chapter Cite Chapter

MLA

Maniadis, Ioannis, et al. "Data Augmentation Using GANs for 3D Applications." Recent Advances in 3D Imaging, Modeling, and Reconstruction, edited by Athanasios Voulodimos and Anastasios Doulamis, IGI Global, 2020, pp. 229-269. https://doi.org/10.4018/978-1-5225-5294-9.ch011

APA

Maniadis, I., Solachidis, V., Vretos, N., & Daras, P. (2020). Data Augmentation Using GANs for 3D Applications. In A. Voulodimos & A. Doulamis (Eds.), Recent Advances in 3D Imaging, Modeling, and Reconstruction (pp. 229-269). IGI Global. https://doi.org/10.4018/978-1-5225-5294-9.ch011

Chicago

Maniadis, Ioannis, et al. "Data Augmentation Using GANs for 3D Applications." In Recent Advances in 3D Imaging, Modeling, and Reconstruction, edited by Athanasios Voulodimos and Anastasios Doulamis, 229-269. Hershey, PA: IGI Global, 2020. https://doi.org/10.4018/978-1-5225-5294-9.ch011

Export Reference

Mendeley
Favorite

Abstract

Modern deep learning techniques have proven that they have the capacity to be successful in a wide area of domains and tasks, including applications related to 3D and 2D images. However, their quality depends on the quality and quantity of the data with which models are trained. As the capacity of deep learning models increases, data availability becomes the most significant. To counter this issue, various techniques are utilized, including data augmentation, which refers to the practice of expanding the original dataset with artificially created samples. One approach that has been found is the generative adversarial networks (GANs), which, unlike other domain-agnostic transformation-based methods, can produce diverse samples that belong to a given data distribution. Taking advantage of this property, a multitude of GAN architectures has been leveraged for data augmentation applications. The subject of this chapter is to review and organize implementations of this approach on 3D and 2D imagery, examine the methods that were used, and survey the areas in which they were applied.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.