AI RESEARCH
PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures
arXiv CS.CV
•
ArXi:2603.11695v1 Announce Type: new 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.