Rapid inverse design of large-scale freeform meta-optics with the neighborhood-attention transformer
Open Access
- 28 September 2026
- journal article
- research article
- Published by Springer Nature in PhotoniX
- Vol. 7 (1) , 69
Abstract
Metasurfaces are progressively reshaping traditional optical paradigms and pushing the boundaries in complex applications where compact designs are essential. However, the design of metasurfaces demands substantial computational resources to numerically solve Maxwell's equations—particularly for large-scale photonic systems. Conventional forward design using electromagnetic solvers is based on specific approximations that may not effectively address complex problems. In contrast, existing inverse design methods are a stepwise process that is often time-consuming. Here, we overcome these challenges by presenting MetaE-former architecture, a Neighborhood Attention Transformer-based transfer learning framework that enables customized surrogate solver development through fine-tuning of pre-trained neural networks with only thousands of data, facilitating highly efficient task-adaptable inverse design of metasurfaces. Moreover, this method achieves global solutions for hundreds of nanostructures simultaneously, providing up to a 250,000-fold speedup during the optimization stage compared with solving for individual meta-atoms based on the FDTD method. As examples, we demonstrate a binarized high-numerical-aperture (~ 1.31) metalens and several optimized structured-light meta-generators. Our method significantly improves the beam shaping adaptability with metasurfaces and paves the way for quick design of large-scale metadevices with high accuracy.Keywords
Funding Information
- Chongqing Municipal Key Research and Development Program of China (2023YFF0722600)
- Chongqing Municipal Key Research and Development Program of China (2022YFA1404300)
- Natural Science Foundation of China (62435007)
- Natural Science Foundation of China (62135003)
- Natural Science Foundation of China (62205267)
- Natural Science Foundation of China (12325411)
- Natural Science Foundation of China (62288101)
- Natural Science Foundation of China (11774162)
- Natural Science Basic Research Program of Shaanxi Province (2024JC-YBMS494)
- Fundamental Research Funds for the Central Universities (xzy012023033)
- Fundamental Research Funds for the Central Universities (020414380175)
- Natural Science Foundation of Jiangsu Province (BK20233001)
- Jiangsu Provincial Key Research and Development Program (BG2024029)
- Research Grant Council of Hong Kong (CRS_HKUST601/23)
- Research Grant Council of Hong Kong (AoE/P-502/20)
This publication has 60 references indexed in Scilit:
- Inverse Design of Aberration-Corrected Hybrid Metalenses for Large Field of View Thermal Imaging Across the Entire Longwave Infrared Atmospheric WindowACS Nano, 2024
- Deep Learning Design for Multiwavelength Infrared Image Sensors Based on Dielectric Freeform MetasurfaceAdvanced Optical Materials, 2023
- High Speed Simulation and Freeform Optimization of Nanophotonic Devices with Physics-Augmented Deep LearningACS Photonics, 2022
- Mass‐Manufactured Beam‐Steering Metasurfaces for High‐Speed Full‐Duplex Optical Wireless‐Broadcasting CommunicationsAdvanced Materials, 2021
- MAXIM: Metasurfaces-oriented electromagnetic wave simulation software with intuitive graphical user interfacesComputer Physics Communications, 2021
- Quo Vadis, Metasurfaces?Nano Letters, 2021
- Deep Learning to Accelerate Scatterer-to-Field Mapping for Inverse Design of Dielectric MetasurfacesACS Photonics, 2021
- Complex Inverse Design of Meta-optics by Segmented Hierarchical Evolutionary AlgorithmACS Nano, 2019
- Nonlinear Holographic All-Dielectric MetasurfacesNano Letters, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015