Super-Resolution of 3D Micro-CT Images Using Generative Adversarial Networks: Enhancing Resolution and Segmentation Accuracy
This work addresses segmentation challenges in digital rock physics, offering incremental improvements for analyzing rock minerals and pore space.
The researchers tackled the problem of low-resolution and segmentation inaccuracies in 3D micro-CT images of rocks by developing a generative model that enhances resolution eightfold and improves segmentation accuracy, achieving a resolution of 0.4375 micro-m/voxel.
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.