Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Media

TL;DR

This paper introduces a diffusion model for electromagnetic inverse design that efficiently generates structured media geometries from target scattering profiles, outperforming traditional optimization methods in speed and accuracy.

Contribution

The authors develop a conditional diffusion model that directly maps desired scattering patterns to metasurface structures, handling non-uniqueness and reducing design time significantly.

Findings

Median MPE below 19% on unseen targets

Outperforms CMA-ES optimization in accuracy

Reduces design time from hours to seconds

Abstract

We present a conditional diffusion model for electromagnetic inverse design that generates structured media geometries directly from target differential scattering cross-section profiles, bypassing expensive iterative optimization. Our 1D U-Net architecture with Feature-wise Linear Modulation learns to map desired angular scattering patterns to 2x2 dielectric sphere structure, naturally handling the non-uniqueness of inverse problems by sampling diverse valid designs. Trained on 11,000 simulated metasurfaces, the model achieves median MPE below 19% on unseen targets (best: 1.39%), outperforming CMA-ES evolutionary optimization while reducing design time from hours to seconds. These results demonstrate that employing diffusion models is promising for advancing electromagnetic inverse design research, potentially enabling rapid exploration of complex metasurface architectures and accelerating the development of next-generation photonic and wireless communication systems. The code is publicly available at https://github.com/mikzuker/inverse_design_metasurface_generation.