Deep learning-driven adaptive optics for laser wavefront correction
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 adaptive optics to optimize beam quality. The robustness and precision of the method are enhanced by applying the concept of phase diversity based on spiral phase plates.
Authors
- Sonam Smitha Ravi
- Volker Rominger
- Daniel Flamm (ORCID: https://orcid.org/0000-0003-2438-5980)
- Stefan Nolte (ORCID: https://orcid.org/0000-0002-2919-2662)
- Jikai Wang (ORCID: https://orcid.org/0000-0003-4340-311X)
- Dominik Bauer
- Sven Burckhard
Institutions
- Leibniz Institute of Photonic Technology (DE)
- Fraunhofer Institute for Applied Optics and Precision Engineering (DE)
- MS-Schramberg (Germany) (DE)
- S&F Systemtechnik (Germany) (DE)
- Friedrich Schiller University Jena (DE)
Publication Details
- Journal
- Applied Optics
- Published
- 2025-09-12
- DOI
- https://doi.org/10.1364/ao.572860
- Primary Topic
- Adaptive optics and wavefront sensing
- Type
- article
- Field-Weighted Citation Impact
- 0.00