Property-Constrained 3D Porous Media Reconstruction from 2D Images via Conditional Generative Adversarial Networks
For geoscientists and engineers, it enables 3D porous media reconstruction without expensive 3D training data, but the method is demonstrated on only two samples and may be incremental.
This work introduces a conditional GAN framework that generates 3D porous media volumes with controlled porosity from 2D thin section images, achieving porosity control with an R² of 0.93 and mean absolute errors of 0.019 and 0.010 on two carbonate samples.
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.