3D Geological Image Synthesis From 2D Examples Using Generative Adversarial Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Frontiers in Water Year : 2020

3D Geological Image Synthesis From 2D Examples Using Generative Adversarial Networks

Abstract

Generative Adversarial Networks (GAN) are becoming an alternative to Multiple-point Statistics (MPS) techniques to generate stochastic fields from training images. But a difficulty for all the training image based techniques (including GAN and MPS) is to generate 3D fields when only 2D training data sets are available. In this paper, we introduce a novel approach called Dimension Augmenter GAN (DiAGAN) enabling GANs to generate 3D fields from 2D examples. The method is simple to implement and is based on the introduction of a random cut sampling step between the generator and the discriminator of a standard GAN. Numerical experiments show that the proposed approach provides an efficient solution to this long lasting problem.

Dates and versions

hal-02992194 , version 1 (06-11-2020)

Identifiers

Cite

Guillaume Coiffier, Philippe Renard, Sylvain Lefebvre. 3D Geological Image Synthesis From 2D Examples Using Generative Adversarial Networks. Frontiers in Water, 2020, 2, ⟨10.3389/frwa.2020.560598⟩. ⟨hal-02992194⟩
130 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More