3D Geological Image Synthesis From 2D Examples Using Generative Adversarial Networks
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...
Main Authors: | Guillaume Coiffier, Philippe Renard, Sylvain Lefebvre |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2020-10-01
|
Series: | Frontiers in Water |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frwa.2020.560598/full |
Similar Items
-
Generating adversarial examples without specifying a target model
by: Gaoming Yang, et al.
Published: (2021-09-01) -
Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks
by: Tuan-Feng Zhang, et al.
Published: (2019-06-01) -
Improving Heterogeneous Network Knowledge Transfer Based on the Principle of Generative Adversarial
by: Feifei Lei, et al.
Published: (2021-06-01) -
Perceptually Similar Image Classification Adversarial Example Generation Model
by: LI Junjie, WANG Qian
Published: (2020-11-01) -
Targeted Speech Adversarial Example Generation With Generative Adversarial Network
by: Donghua Wang, et al.
Published: (2020-01-01)