# Reconstruction of three-dimensional porous media using generative adversarial neural networks

arXiv: https://arxiv.org/abs/1704.03225 · HTML: https://mlsanity.com/paper/1704.03225/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2017.

## Built on by (most cited first, 30 of 36)

- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [Generating 3D structures from a 2D slice with GAN-based dimensionality expansion](https://mlsanity.com/paper/2102.07708/) (2021)
- [Deep Learning in Deterministic Computational Mechanics](https://mlsanity.com/paper/2309.15421/) (2023)
- [Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art](https://mlsanity.com/paper/2308.16316/) (2023)
- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics](https://mlsanity.com/paper/2206.01693/) (2022)
- [Constraining Generative Models for Engineering Design with Negative Data](https://mlsanity.com/paper/2306.15166/) (2023)
- [Spiking neural networks for nonlinear regression](https://mlsanity.com/paper/2210.03515/) (2022)
- [Deep-Learned Generators of Porosity Distributions Produced During Metal Additive Manufacturing](https://mlsanity.com/paper/2205.05794/) (2022)
- [Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions](https://mlsanity.com/paper/2211.08179/) (2022)
- [DA-VEGAN: Differentiably Augmenting VAE-GAN for microstructure reconstruction from extremely small data sets](https://mlsanity.com/paper/2303.03403/) (2023)
- [Multi-Scale Simulation of Complex Systems: A Perspective of Integrating Knowledge and Data](https://mlsanity.com/paper/2306.10275/) (2023)
- [Controlled Latent Diffusion Models for 3D Porous Media Reconstruction](https://mlsanity.com/paper/2503.24083/) (2025)
- [When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges](https://mlsanity.com/paper/2402.03349/) (2024)
- [RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation](https://mlsanity.com/paper/2108.03132/) (2021)
- [Morphology Decoder: A Machine Learning Guided 3D Vision Quantifying Heterogenous Rock Permeability for Planetary Surveillance and Robotic Functions](https://mlsanity.com/paper/2111.13460/) (2021)
- [Generating unrepresented proportions of geological facies using Generative Adversarial Networks](https://mlsanity.com/paper/2203.09639/) (2022)
- [A stable deep adversarial learning approach for geological facies generation](https://mlsanity.com/paper/2305.13318/) (2023)
- [Pix2Geomodel: A Next-Generation Reservoir Geomodeling with Property-to-Property Translation](https://mlsanity.com/paper/2506.17747/) (2025)
- [PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets](https://mlsanity.com/paper/2204.05114/) (2022)
- [ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis](https://mlsanity.com/paper/2304.04291/) (2023)
- [Computationally Efficient Multiscale Neural Networks Applied To Fluid Flow In Complex 3D Porous Media](https://mlsanity.com/paper/2102.07625/) (2021)
- [Seismic Inverse Modeling Method based on Generative Adversarial Network](https://mlsanity.com/paper/2106.04197/) (2021)
- [Deducing Optimal Classification Algorithm for Heterogeneous Fabric](https://mlsanity.com/paper/2111.05558/) (2021)
- [Generation of non-stationary stochastic fields using Generative Adversarial Networks](https://mlsanity.com/paper/2205.05469/) (2022)
- [Multiscale reconstruction of porous media based on multiple dictionaries learning](https://mlsanity.com/paper/2205.08278/) (2022)
- [Two approaches to inpainting microstructure with deep convolutional generative adversarial networks](https://mlsanity.com/paper/2210.06997/) (2022)
- [Mitigation of Spatial Nonstationarity with Vision Transformers](https://mlsanity.com/paper/2212.04633/) (2022)
- [Constrained Transformer-Based Porous Media Generation to Spatial Distribution of Rock Properties](https://mlsanity.com/paper/2410.21462/) (2024)
- [Conditional Deep Generative Models for Belief State Planning](https://mlsanity.com/paper/2505.11698/) (2025)

## Abstract (arXiv)

To evaluate the variability of multi-phase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a novel method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image datasets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that GANs can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.