GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization
ACM Transactions on Graphics · 03.07.2026 · 45 (4) · 1-15
DOI: 10.1145/3811333 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 03.07.2026. Verfasst von Yu Xing und 3 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Lattice metamaterials enable lightweight, multifunctional structures, yet homogenization-based evaluation of their effective properties remains computationally expensive. Neural surrogates offer speed but often lack the accuracy and stability required for engineering-grade simulations. We introduce GMT, a G eometric M ultigrid T ransformer - a neural solver with high numerical fidelity for fast and reliable lattice homogenization. GMT achieves architectural alignment with Geometric Multigrid (GMG) by restructuring Point Transformer V3 to operate across sparse GMG hierarchies, capturing long-range dependencies and cross-level interactions essential for multigrid convergence. To enforce physical consistency, GMT incorporates physics-aware positional encoding for strict enforcement of periodicity and predicts both the finest-level solution and multi-level residual corrections. These predictions deliver a spectrally-aligned initialization , enabling end-to-end training under physics-informed and solver-aware losses and requiring only a single GMG V-cycle refinement to reach convergence. This fusion of neural prediction and numerical rigor achieves relative residual errors of 10 -5 with a 160× speedup over state-of-the-art GPU-based solvers at equivalent accuracy - particularly at high resolutions (e.g. , 512 3 ), where traditional methods become most costly. We validate GMT across mechanical and thermal domains, demonstrate robust generalization to unseen geometries and non-periodic settings, and showcase scalability to high resolutions - enabling real-time design iteration, multi-scale simulations, high-throughput material discovery, and inverse design.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xing, Y., Liu, Y., Xue, T., & Lu, L. (2026). GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization. ACM Transactions on Graphics, 45(4), 1-15. https://doi.org/10.1145/3811333
Vancouver
Xing Y, Liu Y, Xue T, Lu L. GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization. ACM Transactions on Graphics. 2026;45(4):1-15. doi:10.1145/3811333
BibTeX
@article{Xing2026,
author = {Xing, Yu and Liu, Yang and Xue, Tianyang and Lu, Lin},
title = {GMT: A Geometric Multigrid Transformer Solver for Microstructure Homogenization},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {4},
pages = {1--15},
doi = {10.1145/3811333}
}
EUVIMED