Denoising wavefront sensor images with deep neural networks

B. Pou; E. Quiñones; D. Gratadour; M. Martin

doi:10.1117/12.2576242

Translator Disclaimer

13 December 2020 Denoising wavefront sensor images with deep neural networks

B. Pou, E. Quiñones, D. Gratadour, M. Martin

Author Affiliations +

Proceedings Volume 11448, Adaptive Optics Systems VII; 114484J (2020) https://doi.org/10.1117/12.2576242
Event: SPIE Astronomical Telescopes + Instrumentation, 2020, Online Only

Conference Poster

Abstract

A classical closed-loop adaptive optics system with a Shack-Hartmann wavefront sensor (WFS) relies on a center of gravity approach to process the WFS information and an integrator with gain to produce the commands to a Deformable Mirror (DM) to compensate wavefront perturbations. In this kind of systems, noise in the WFS images can propagate to errors in centroids computation, and thus, lead the AO system to perform poorly in closed-loop operations. In this work, we present a deep supervised learning method to denoise the WFS images based on convolutional denoising autoencoders. Our method is able to denoise the images up to a high noise level and improve the integrator performance almost to the level of a noise-free situation.

Citation Download Citation

B. Pou, E. Quiñones, D. Gratadour, and M. Martin "Denoising wavefront sensor images with deep neural networks", Proc. SPIE 11448, Adaptive Optics Systems VII, 114484J (13 December 2020); https://doi.org/10.1117/12.2576242

ACCESS THE FULL ARTICLE