Metasurface-based Terahertz Three-dimensional Holography Enabled by Physics-Informed Neural Network

TL;DR

This paper introduces a physics-informed neural network for rapid, high-quality 3D holographic metasurface design in the terahertz range, capable of generalizing across various configurations without retraining.

Contribution

The proposed LM-PINN model enables fast, dataset-free, and adaptable design of 3D holographic metasurfaces, surpassing traditional iterative methods in speed and flexibility.

Findings

LM-PINN achieves higher imaging quality than traditional algorithms.

Inference time is typically less than 1 second, significantly faster than conventional methods.

The model generalizes across different physical setups without retraining.

Abstract

Artificial intelligence has revolutionized optical device design, overcoming the efficiency bottlenecks of traditional methods. For holographic metasurfaces, conventional iterative algorithms suffer from time-consuming iterations and convergence stagnation, especially as the complexity of 3D target fields increases. While recent deep-learning-based algorithms have improved the trade-off between speed and image quality, most existing models remain constrained by predefined physical scenarios (e.g., fixed distances), limiting their adaptability in dynamic practical applications. To address these challenges, we propose a physics-informed neural network (PINN) based on local polynomial fitting and multi-plane wave propagation (LM-PINN) for the rapid design of terahertz 3D holographic metasurfaces. By leveraging a self-supervised training strategy, LM-PINN eliminates the need for labeled datasets, enabling direct end-to-end mapping from target holographic patterns to the metasurface structures. Both simulated and experimental results demonstrate that LM-PINN-designed metasurfaces offer higher imaging quality than traditional iterative algorithms. Crucially, by incorporating a distance encoding process, a single trained LM-PINN generalizes effectively across diverse physical configurations, including varying diffraction distances and distinct 2D or 3D targets, eliminating the necessity for retraining. Furthermore, the inference process of LM-PINN typically takes less than 1 second, providing a multifold speed advantage over traditional algorithms. Consequently, this strategy offers a robust and universal framework that paves the way for high-quality, real-time, and large-scale 3D holographic technologies.