# Generating 3D images of material microstructures from a single 2D image: a denoising diffusion approach

Article · Johan Phan, Muhammad Sarmad, Leonardo Carlos Ruspini, Gabriel Hanssen Kiss, Frank Lindseth

- Archive id: doi:10.1038/s41598-024-56910-9
- Published: 2024-03-18
- Venue: Scientific Reports
- DOI: https://doi.org/10.1038/s41598-024-56910-9
- PMID: 38499588
- Citations: 40
- Source URL: https://doi.org/10.1038/s41598-024-56910-9
- PDF: https://www.nature.com/articles/s41598-024-56910-9.pdf
- Provenance: openalex

## Abstract

Three-dimensional (3D) images provide a comprehensive view of material microstructures, enabling numerical simulations unachievable with two-dimensional (2D) imaging alone. However, obtaining these 3D images can be costly and constrained by resolution limitations. We introduce a novel method capable of generating large-scale 3D images of material microstructures, such as metal or rock, from a single 2D image. Our approach circumvents the need for 3D image data while offering a cost-effective, high-resolution alternative to existing imaging techniques. Our method combines a denoising diffusion probabilistic model with a generative adversarial network framework. To compensate for the lack of 3D training data, we implement chain sampling, a technique that utilizes the 3D intermediate outputs obtained by reversing the diffusion process. During the training phase, these intermediate outputs are guided by a 2D discriminator. This technique facilitates our method's ability to gradually generate 3D images that accurately capture the geometric properties and statistical characteristics of the original 2D input. This study features a comparative analysis of the 3D images generated by our method, SliceGAN (the current state-of-the-art method), and actual 3D micro-CT images, spanning a diverse set of rock and metal types. The results shown an improvement of up to three times in the Frechet inception distance score, a typical metric for evaluating the performance of image generative models, and enhanced accuracy in derived properties compared to SliceGAN. The potential of our method to produce high-resolution and statistically representative 3D images paves the way for new applications in material characterization and analysis domains.

_Abstract reproduced under CC-BY (publisher license, via OpenAlex)._

Topics: [Generative & Multimodal Models](https://space-kitty.com/topics/generative-multimodal)

---
Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.