Denoising diffusion-based synthetic generation of three-dimensional (3D) anisotropic microstructures from two-dimensional (2D) micrographs.

Integrated computational materials engineering (ICME) has significantly enhanced the systemic analysis of the relationship between microstructure and material properties, paving the way for developing high-performance materials. However, analyzing microstructure-sensitive material behavior remains challenging due to the scarcity of three-dimensional (3D) microstructure datasets. Moreover, this challenge is intensified if the microstructure is anisotropic, as this also results in anisotropic material properties. This paper presents a framework for reconstructing anisotropic microstructures solely based on two-dimensional (2D) micrographs using conditional diffusion-based generative models (DGMs). The proposed framework involves the spatial connection of multiple 2D conditional DGMs, each trained to generate 2D microstructure samples for three orthogonal planes. The connected multiple reverse diffusion processes then enable effective modeling of a Markov chain for transforming noise into a 3D microstructure sample. Furthermore, a modified harmonized sampling enhances the sample quality while preserving the spatial connection between the slices of anisotropic microstructure samples in 3D space. The 2D-to-3D reconstructed anisotropic microstructure samples are evaluated regarding the spatial correlation function and the physical material behavior to validate the proposed framework. The results demonstrate that the framework can reproduce the statistical distribution of material phases and properties in 3D space. It highlights the potential application of the proposed 2D-to-3D reconstruction framework in establishing microstructure-property linkages, which could aid high-throughput material design for future studies. [ABSTRACT FROM AUTHOR]