Publications by authors named "Ekaterina Muravleva"
Article Synopsis
- The study addresses the challenge of analyzing rock at the microlevel when obtaining a large number of sample materials is difficult.
- A deep learning model is proposed for reconstructing 3D porous structures from 2D slices by fitting a distribution based on existing samples.
- The method, implemented using a neural network architecture, demonstrates effective reconstruction accuracy through numerical testing based on Minkowski functionals.
This work considers the usage of StyleGAN architecture for the task of microstructure synthesis. The task is the following: Given number of samples of structure we try to generate similar samples at the same time preserving its properties. Since the considered architecture is not able to produce samples of sizes larger than the training images, we propose to use image quilting to merge fixed-sized samples.
View Article and Find Full Text PDF