The inverse design of microstructures plays a pivotal role in optimizing metamaterials with specific, targeted physical properties. While traditional forward design methods are constrained by their inability to explore the vast combinatorial design space, inverse design offers a compelling alternative by directly generating structures that fulfill predefined performance criteria. However, achieving precise control over both geometry and material properties remains a significant challenge due to their intricate interdependence. Existing approaches, which typically rely on voxel or parametric representations, often limit design flexibility and structural diversity. In this work, we present a novel generative model that integrates latent diffusion with Holoplane, an advanced hybrid neural representation that simultaneously encodes both geometric and physical properties. This combination ensures superior alignment between geometry and properties. Our approach generalizes across multiple microstructure classes, enabling the generation of diverse, tileable microstructures with significantly improved property accuracy and enhanced control over geometric validity, surpassing the performance of existing methods. We introduce a multi-class dataset encompassing a variety of geometric morphologies, including truss, shell, tube, and plate structures, to train and validate our model. Experimental results demonstrate the model’s ability to generate microstructures that meet target properties, maintain geometric validity, and integrate seamlessly into complex assemblies. Additionally, we explore the potential of our framework through the generation of new microstructures, cross-class interpolation, and the infilling of heterogeneous microstructures. Code and data for this paper are at https://github.com/TimHsue/MIND.
@inproceedings{Xue2025MIND,
author = {Xue, Tianyang and Liu, Longdu and Lu, Lin and Henderson, Paul and Tang, Pengbin and Li, Haochen and Liu, Jikai and Zhao, Haisen and Peng, Hao and Bickel, Bernd},
title = {MIND: Microstructure INverse Design with Generative Hybrid Neural Representation},
year = {2025},
isbn = {9798400715402},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3721238.3730682},
doi = {10.1145/3721238.3730682},
booktitle = {ACM SIGGRAPH 2025 Conference Papers},
numpages = {12},
keywords = {microstructures, generative design, neural networks, additive manufacturing},
location = {Vancouver, BC, Canada},
series = {SIGGRAPH '25}
}
We thank all reviewers for their valuable comments and constructive suggestions. We are also grateful to Prof. Niloy J. Mitra for his insightful discussions, and to Dr. Lingxin Cao and Yu Xing for their assistance with the simulations and for proofreading the paper. This work is supported in part by grants from National Key Research and Development Program of China (Grant No. 2024YFB3309500), Key Research Project of Zhejiang Lab (Grant No. 3700-3AA240100), and National Natural Science Foundation of China (Grant Nos. 62472258, U23A20312, 62472257).