Improving Generative Inverse Design of Rectangular Patch Antennas with Test Time Optimization

TL;DR

This paper introduces a two-stage deep learning framework for inverse antenna design that combines generative modeling with test-time optimization to improve accuracy and accommodate multiple design objectives.

Contribution

It presents a novel generative modeling approach for antenna design that integrates test-time optimization for enhanced accuracy and flexibility.

Findings

Test-time optimization improves design accuracy.

Framework generalizes to various design criteria.

Method adapts to complex geometric spaces.

Abstract

We propose a two-stage deep learning framework for the inverse design of rectangular patch antennas. Our approach leverages generative modeling to learn a latent representation of antenna frequency response curves and conditions a subsequent generative model on these responses to produce feasible antenna geometries. We further demonstrate that leveraging search and optimization techniques at test-time improves the accuracy of the generated designs and enables consideration of auxiliary objectives such as manufacturability. Our approach generalizes naturally to different design criteria, and can be easily adapted to more complex geometric design spaces.