Real-time phase-retrieval and wavefront sensing enabled by an artificial neural network

TL;DR

This paper presents a neural network-based method for real-time wavefront reconstruction from diffraction patterns, enabling rapid adaptive optics adjustments and outperforming traditional iterative methods especially under noisy conditions.

Contribution

The authors introduce a neural network trained on simulated data for fast, real-time wavefront sensing from diffraction patterns, significantly reducing computation time and improving noise robustness.

Findings

Real-time wavefront reconstruction within milliseconds.

Neural network outperforms iterative methods in noisy conditions.

Enables adaptive optics correction in live systems.

Abstract

In this manuscript we demonstrate a method to reconstruct the wavefront of focused beams from a measured diffraction pattern behind a diffracting mask in real-time. The phase problem is solved by means of a neural network, which is trained with simulated data and verified with experimental data. The neural network allows live reconstructions within a few milliseconds, which previously with iterative phase retrieval took several seconds, thus allowing the adjustment of complex systems and correction by adaptive optics in real time. The neural network additionally outperforms iterative phase retrieval with high noise diffraction patterns.