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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Chi, Jiang, Tianle, Wei, Xiaodong, Wang, Yanming
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908881763958784
author Chen, Chi
Jiang, Tianle
Wei, Xiaodong
Wang, Yanming
author_facet Chen, Chi
Jiang, Tianle
Wei, Xiaodong
Wang, Yanming
contents 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 $R^2$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11695
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures
Chen, Chi
Jiang, Tianle
Wei, Xiaodong
Wang, Yanming
Computer Vision and Pattern Recognition
Materials Science
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 $R^2$ 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.
title PolyCrysDiff: Controllable Generation of Three-Dimensional Computable Polycrystalline Material Structures
topic Computer Vision and Pattern Recognition
Materials Science
url https://arxiv.org/abs/2603.11695