Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model
cs.AI
Submitted: 2026-09-17
Updated: 2026-09-17
Code: https://github.com/40uf411/DimExDAM
License: http://creativecommons.org/licenses/by/4.0/
The gist: Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal.
Terminology
Abstract
Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal. Property simulation typically calls for 3D imaging, which is expensive, not always accessible, and technically limited for certain materials. Recent progress in deep generative models offers a way around this, reconstructing 3D volumes from the more easily acquired 2D images. Among GAN-based methods for 3D microstructure generation, SliceGAN has shown strong results for homogeneous isotropic and anisotropic systems. It struggles, however, to capture the finer detail of more complex heterogeneous microstructures, which motivates alternative generative frameworks. We introduce a hybrid approach that draws on the stability and generation quality of denoising diffusion models. Since no 3D ground truth is available, we replace the standard denoising loss with an adversarial loss, which yields a stable training process in our experiments. We show that the resulting model generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.
Sources
- 3D Multiphase Heterogeneous Microstructure Generation Using Conditional Latent Diffusion Models
- Layer rotation: a surprisingly powerful indicator of generalization in deep networks?
- Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
- Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
- Denoising Diffusion Probabilistic Models
- Elucidating the Design Space of Diffusion-Based Generative Models
- A Style-Based Generator Architecture for Generative Adversarial Networks
- Auto-Encoding Variational Bayes
- Which Training Methods for GANs do actually Converge?
- An Introduction to Convolutional Neural Networks
- Multi-objective evolutionary GAN for tabular data synthesis
- Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directions
- Denoising Diffusion Implicit Models
- Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection