Deep learning-driven adaptive optics for laser wavefront correction
Optics
2025-09-16 v1
Abstract
{We report on an intensity-only and deep-learning based method for laser beam characterization that allows to predict the underlying optical field within milliseconds. A simple near-field / far-field camera setup enables online control of an adaptive optics to optimize beam quality. The robustness and precision of the method is enhanced by applying the concept of phase diversity based on spiral phase plates.
Cite
@article{arxiv.2509.10662,
title = {Deep learning-driven adaptive optics for laser wavefront correction},
author = {Jikai Wang and Sven Burckhard and Sonam Smitha Ravi and Dominik Bauer and Volker Rominger and Stefan Nolte and Daniel Flamm},
journal= {arXiv preprint arXiv:2509.10662},
year = {2025}
}
Comments
Accepted manuscript (Applied Optics)