English

PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures

Computer Vision and Pattern Recognition 2026-03-13 v1 Materials Science

Abstract

The three-dimensional (3D) microstructures of polycrystalline materials exert a critical influence on their mechanical and physical properties. Realistic, controllable construction of these microstructures is a key step toward elucidating structure-property relationships, yet remains a formidable challenge. Herein, we propose PolyCrysDiff, a framework based on conditional latent diffusion that enables the end-to-end generation of computable 3D polycrystalline microstructures. Comprehensive qualitative and quantitative evaluations demonstrate that PolyCrysDiff faithfully reproduces target grain morphologies, orientation distributions, and 3D spatial correlations, while achieving an R2R^2 over 0.972 on grain attributes (e.g., size and sphericity) control, thereby outperforming mainstream approaches such as Markov random field (MRF)- and convolutional neural network (CNN)-based methods. The computability and physical validity of the generated microstructures are verified through a series of crystal plasticity finite element method (CPFEM) simulations. Leveraging PolyCrysDiff's controllable generative capability, we systematically elucidate how grain-level microstructural characteristics affect the mechanical properties of polycrystalline materials. This development is expected to pave a key step toward accelerated, data-driven optimization and design of polycrystalline materials.

Keywords

Cite

@article{arxiv.2603.11695,
  title  = {PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures},
  author = {Chi Chen and Tianle Jiang and Xiaodong Wei and Yanming Wang},
  journal= {arXiv preprint arXiv:2603.11695},
  year   = {2026}
}
R2 v1 2026-07-01T11:16:14.857Z