Property-Constrained 3D Porous Media Reconstruction from 2D Images via Conditional Generative Adversarial Networks

2026-07-02

AI Summary

This work addresses the challenge of reconstructing three-dimensional porous media with controllable porosity from only two-dimensional slice images, without reliance on expensive 3D training data. The authors propose a novel conditional generative adversarial network framework that uniquely integrates attribute-conditioned generation with 2D-to-3D reconstruction. Their approach employs a hybrid architecture featuring a 3D generator and a 2D discriminator, complemented by multi-axis slice extraction and an enhanced U-Net segmentation module. This method enables precise control over rock porosity while preserving 3D structural consistency, achieving strong performance on two types of carbonate rock samples: a porosity control coefficient of determination (R²) of 0.93, and mean absolute errors of 0.019 and 0.010 for heterogeneous and homogeneous samples, respectively.

Abstract

This study presents a conditional Generative Adversarial Network (cGAN) framework for generating 3D porous media volumes with controlled porosity, trained exclusively on 2D thin section images. The key innovation lies in combining property-conditioned generation with 2D-to-3D reconstruction, eliminating the need for expensive 3D training data while maintaining control over petrophysical properties. The framework employs a hybrid architecture with a 3D generator and 2D discriminator, where multi-axis slice extraction enables learning 3D-consistent structures from 2D training data. Porosity labels are extracted using an Enhanced U-Net segmentation model. The methodology was demonstrated on two carbonate samples with different lithologies: dolomite-anhydrite and pure dolomite. Results show that the framework successfully generates realistic 3D volumes capturing lithological features such as anhydrite inclusions and fine crystalline textures. Porosity control achieved an $R^2$ of 0.93, with mean absolute errors of 0.019 and 0.010 for the heterogeneous and homogeneous samples, respectively.

Problem

• 3D porous media reconstruction
• porosity control
• 2D-to-3D generation
• conditional generative adversarial networks
• petrophysical properties

Innovation

• conditional GAN
• 3D porous media reconstruction
• porosity control
• 2D-to-3D generation
• multi-axis slice extraction