arxiv.orgpaperGenerating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
This paper proposes a hybrid generative model that combines denoising diffusion with an adversarial loss (replacing the standard denoising loss, since no 3D ground truth exists) to synthesize 3D geological/material microstructures from 2D image slices. It targets heterogeneous clay and cementitious materials, where the prior GAN-based approach SliceGAN struggles to capture fine detail, and shows the new model produces volumes with fewer slice artefacts and closer agreement to ground-truth phase fractions and structural descriptors.
TL;DR A diffusion-adversarial hybrid model reconstructs realistic 3D heterogeneous material microstructures from 2D images, outperforming SliceGAN on complex materials.
Technologies named here
- SliceGAN
- Stable Diffusion
- Generative Adversarial Network
Techniques named here
- Stable diffusion-adversarial hybrid model
- Denoising diffusion model
Related in research