Transfer learning-based techniques for efficient 3D-reconstruction of functionally graded materials

• Developing a novel transfer learning to achieve interpolation-based 3D reconstruction for functionally graded materials (FGM). • The approach implemented to the functionally graded LSM microstructure and 3D microstructure of FGM microstructure. • The reconstruction accuracy is evaluated by calculating the lineal path, two-point correlation and quality of connection functions for the microstructures. The various properties and phenomena in materials significantly depend on the high-quality three-dimensional (3D) microstructure. This paper proposes a novel method for 3D reconstruction of functionally graded materials (FGMs) using transfer learning techniques to overcome the limitations of experimental 3D microscopy. The approach begins by interpolating 2D cross-sectional images of FGM microstructures through a hybrid deep learning method combining StyleGAN and Gatys techniques, generating intermediate images based on style and content. In the next step, transfer learning is applied using convolutional occupancy networks to reconstruct the 3D microstructure from the 2D image depth layers, with the model trained on point clouds obtained from 2D images. To validate the method, the reconstructed microstructures are compared to actual material images at the same depth using various metrics, including lineal path, two-point correlation, and quality of connection functions. The results show a high degree of accuracy, indicating that the reconstructed images closely match the target microstructures. Finally, to show the application of model the approach is implemented to the functionally graded lanthanum strontium manganite (LSM) and 3D microstructure of this FGM has been extracted using the approach