Two approaches to inpainting microstructure with deep convolutional generative adversarial networks
This addresses the issue of inaccurate simulation or feature analysis in materials science due to imaging defects, though it appears incremental as it builds on existing GAN-based inpainting approaches.
The paper tackles the problem of defects in microstructural images by introducing two deep convolutional generative adversarial network methods for inpainting, which generate synthetic microstructure to replace occluded regions with matching boundaries, resulting in one method offering high speed and simplicity and the other providing smoother boundaries.
Imaging is critical to the characterisation of materials. However, even with careful sample preparation and microscope calibration, imaging techniques are often prone to defects and unwanted artefacts. This is particularly problematic for applications where the micrograph is to be used for simulation or feature analysis, as defects are likely to lead to inaccurate results. Microstructural inpainting is a method to alleviate this problem by replacing occluded regions with synthetic microstructure with matching boundaries. In this paper we introduce two methods that use generative adversarial networks to generate contiguous inpainted regions of arbitrary shape and size by learning the microstructural distribution from the unoccluded data. We find that one benefits from high speed and simplicity, whilst the other gives smoother boundaries at the inpainting border. We also outline the development of a graphical user interface that allows users to utilise these machine learning methods in a 'no-code' environment.