Research Data
Data Publication
True 2D-to-3D Reconstruction of Heterogenous Porous Media via Deep Generative Adversarial Networks (GANs)
Hannah Vogel | Hamed Amiri
Utrecht University
(2024)
Descriptions
[The latest version of this dataset is accessible via the following DOI: https://doi.org/10.24416/UU01-AFP38O] We imaged samples of Berea sandstone from Ohio (USA) using two 2D imaging techniques: backscattered electron (BSE) and optical microscopy, and 3D X-ray (micro-)computed tomography (XCT). The goal is to employ a deep-learning-based generative model called a generative adversarial network (GAN) to reconstruct statistically equivalent microstructures in 3D from exclusively 2D training images. To evaluate the reconstruction accuracy, we conduct a visual and statistical analysis comparing reconstructions with a 3D X-ray tomography of the same sample. Unlike previous research, our method uses true 2D images from three orthogonally oriented planes for training the model. The data are organized into 10 folders: three contain the original segmented (binary) images of Berea sandstone samples, and the other 7 folders contain data and individual figures used to create figures in the main publication. Link to GitHub containing codes: https://github.com/hamediut/2D-to3D-recon
Keywords
Originally assigned keywords
Microscopy and tomography data
sandstone
Scanning Electrone Microscope
Optical Microscope
Permeability
backscattered electron microscopy
scanning electron microscopy
optical microscopy
X-ray tomography
Micro-CT
image reconstruction
statistically-equivalent microstructures
2D-to-3D reconstruction
deep learning (DL)
microstructural quantification
generative adversarial network (GAN)
artificial intelligence (AI)
Berea sandstone
porous media
Link to GitHub containing codes: https://github.com/hamediut/2D-to3D-recon
Corresponding MSL vocabulary keywords
sandstone
scanning electron microscope (SEM)
optical microscopy
permeability
backscatter electron (BSE) imaging
X-ray tomography
computed tomography (CT)
Berea sandstone
MSL enriched keywords
sedimentary rock
sandstone
Apparatus
electron microscopy
scanning electron microscope (SEM)
optical microscopy
Measured property
permeability
Technique
imaging (2D)
backscatter electron (BSE) imaging
X-ray tomography
imaging (3D)
computed tomography (CT)
wacke
Berea sandstone
Metadata
MSL enriched sub domains
microscopy and tomography
rock and melt physics
Resource Type
Source publisher
| Utrecht University |
DOI
| 10.24416/uu01-do6lt4 |
Creators
| Hannah Vogel |
| Personal |
| Utrecht University |
| Hamed Amiri |
| Personal |
| Utrecht University |
Contributors
| Vogel, Hannah |
| Personal |
| Utrecht University |
| Amiri, Hamed |
| Personal |
| Utrecht University |
| Personal |
| Utrecht University |
Citation
Vogel, H., & Amiri, H. (2024). True 2D-to-3D Reconstruction of Heterogenous Porous Media via Deep Generative Adversarial Networks (GANs) (Version 1.0) [Data set]. Utrecht University. https://doi.org/10.24416/UU01-DO6LT4
References
| URL |
| IsSupplementTo |
Dates
| Issued | 2024-02-16T15:33:02 |
| Updated | 2026-02-04T10:55:53 |
| Collected | 2022-03-01/2024-02-09 |
Language
en
Funding References
| Funder Name | European Research Council |
| Funder Name | NWO |
Rights
| Name | Open - freely retrievable |
| URI | info:eu-repo/semantics/openAccess |
| Name | Creative Commons Attribution 4.0 International |
| URI | https://creativecommons.org/licenses/by/4.0/legalcode |
| Identifier | cc-by-4.0 |
| Identifier Scheme | SPDX |
| Scheme URI | https://spdx.org/licenses/ |
Locations
- no geo-locations found -