TorchOptics: An open-source Python library for differentiable Fourier optics simulations

TL;DR

TorchOptics is an open-source Python library that leverages PyTorch for differentiable Fourier optics simulations, enabling efficient modeling, analysis, and inverse design of complex optical systems with GPU acceleration.

Contribution

It introduces a comprehensive framework for differentiable Fourier optics simulations in Python, integrating optical modeling with machine learning for inverse design and optimization.

Findings

Supports GPU-accelerated tensor computations

Enables gradient-based optimization of optical systems

Includes diverse optical elements and polarization support

Abstract

TorchOptics is an open-source Python library for differentiable Fourier optics simulations, developed using PyTorch to enable GPU-accelerated tensor computations and automatic differentiation. It provides a comprehensive framework for modeling, analyzing, and designing optical systems using Fourier optics, with applications in imaging, diffraction, holography, and signal processing. The library leverages PyTorch's automatic differentiation engine for gradient-based optimization, enabling the inverse design of complex optical systems. TorchOptics supports end-to-end optimization of hybrid models that integrate optical systems with machine learning architectures for digital post-processing. The library includes a wide range of optical elements and spatial profiles, and supports simulations with polarized light and fields with arbitrary spatial coherence.