Super-Resolution of 3D Micro-CT Images Using Generative Adversarial Networks: Enhancing Resolution and Segmentation Accuracy

Evgeny Ugolkov, Xupeng He, Hyung Kwak, Hussein Hoteit
1/12/2025
eess.IVcs.CVcs.LG

No official code found. Best implementation: EvgenyUgolkov/8x_Super-Resolution (7 stars, last commit 2025-02-11).

Abstract

We develop a procedure for substantially improving the quality of segmented 3D micro-Computed Tomography (micro-CT) images of rocks with a Machine Learning (ML) Generative Model. The proposed model enhances the resolution eightfold (8x) and addresses segmentation inaccuracies due to the overlapping X-ray attenuation in micro-CT measurement for different rock minerals and phases. The proposed generative model is a 3D Deep Convolutional Wasserstein Generative Adversarial Network with Gradient Penalty (3D DC WGAN-GP). The algorithm is trained on segmented 3D low-resolution micro-CT images and segmented unpaired complementary 2D high-resolution Laser Scanning Microscope (LSM) images. The algorithm was demonstrated on multiple samples of Berea sandstones. We achieved high-quality super-resolved 3D images with a resolution of 0.4375 micro-m/voxel and accurate segmentation for constituting minerals and pore space. The described procedure can significantly expand the modern capabilities of digital rock physics.

View on arXivView PDF

Code Implementations(1)

EvgenyUgolkov/8x_Super-ResolutionCommunity100%

Contains the code for the "Super-Resolution of 3D Micro-CT Images Using Generative Adversarial Networks: Enhancing Resolution and Segmentation Accuracy" paper

70PythonOct 27, 20241 years ago

Similar Papers

Memory-Efficient Super-Resolution of 3D Micro-CT Images Using Octree-Based GANs: Enhancing Resolution and Segmentation Accuracy

94% match2025

A Generative Machine Learning Model for Material Microstructure 3D Reconstruction and Performance Evaluation

82% match2024

A Decade of Generative Adversarial Networks for Porous Material Reconstruction

80% match2026

Three-dimensional visualization of X-ray micro-CT with large-scale datasets: Efficiency and accuracy for real-time interaction

79% match2026

Automated 3D Tumor Segmentation using Temporal Cubic PatchGAN (TCuP-GAN)

79% match2023

Capability enhancement of the X-ray micro-tomography system via ML-assisted approaches

79% match2024

Cite this paper

@article{ugolkov2025superresolution,
  title  = {Super-Resolution of 3D Micro-CT Images Using Generative Adversarial Networks: Enhancing Resolution and Segmentation Accuracy},
  author = {Evgeny Ugolkov and Xupeng He and Hyung Kwak and Hussein Hoteit},
  year   = {2025},
  eprint = {2501.06939},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.06939v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.06939.svg)](https://codeofpaper.com/paper/2501.06939)

Discussion