Reconstruction of 3D Random Media from 2D Images: Generative Adversarial Learning Approach.

This paper presents an algorithm for stochastic reconstruction of three-dimensional material microstructure from its single two-dimensional cross-sectional image, based on the neural network operating on a principle of generative adversarial learning. The novelty of the proposed algorithm is in introduction of the reconstruction error, which is invariant to translational and rotational transformations and increases stability of the neural-network training and quality of generated structures. It is shown that a use of variational autoencoder helps to extract useful features from a cross-sectional image and provide additional information to a generator for accurate structure reconstruction. A set of 3D microstructures with corresponding 2D slice from each of them is required for model training. The model was trained and tested on sets of binary microstructures of porous materials with open-cell and closed-cell internal morphology. The obtained results for statistical evaluation of material microstructure demonstrate the effectiveness of the proposed algorithm. • Reconstruction of a digital 3D structure from 2D images is important when only images of material's surface are available. • A range of problems that can be solved with neural networks greatly increased, including image synthesis. • A generative adversarial neural network can extract features from the cross-section and reconstruct a 3D microstructure. • Quality of generated images can be evaluated via statistical descriptors. • The developed method was successfully tested for the case studies of open-cell and closed-cell porous structures. [ABSTRACT FROM AUTHOR]