Reconstruction of 3D Porous Media From 2D Slices

Denis Volkhonskiy1Ekaterina Muravleva1Oleg Sudakov1Denis Orlov1Boris Belozerov2Vladislav Krutko2Evgeny Burnaev1Dmitry Koroteev2

1Skolkovo Institute of Science and Technology2Gazprom Neft Science & Technology Center

arXiv 2019

Generated 3D samples of three different types: Berea, Ketton, South-Russian sandstone


We propose a novel deep learning architecture for three-dimensional porous media structure reconstruction from two-dimensional slices. A high-level idea is that we fit a distribution on all possible three-dimensional structures of a specific type based on the given dataset of samples. Then, given partial information (central slices) we recover the three-dimensional structure that is built around such slices. Technically, it is implemented as a deep neural network with encoder, generator and discriminator modules. Numerical experiments show that this method gives a good reconstruction in terms of Minkowski functionals.




If you have any questions about this work, please contact us under