Fusion of Complementary 2D and 3D Mesostructural Datasets Using Generative Adversarial Networks (Adv. Energy Mater. 2/2023)

Imaging It is hard to obtain mesostructural image data with sufficient contrast, resolution, and field-of-view from a single imaging technique. In article number 2202407, Amir Dahari, Samuel J. Cooper and co-workers present a method for combining information from pairs of complementary 2D and 3D imaging techniques in order to accurately reconstruct the desired volumes. The method uses generative adversarial networks to perform super-resolution, style-transfer, and dimensionality expansion.