DOAJ Open Access 2025

Wavefront Reconstruction by its Slopes via Physics-Informed Neural Networks

T. E. Romanenko A. V. Razgulin N. G. Iroshnikov A. V. Larichev

Abstrak

The problem of wavefront reconstruction by its slopes, related to the the phase recovery of a light wave based on Shack-Hartmann sensor data, is considered. A reconstruction method based on the application of physics-informed neural networks to slope measurement data on both regular and irregular grids in two modifications WRPINN and WRRADPINN is proposed. A comparison with the reconstruction method based on the variational approach combined with the projection method using a fractional smoothness stabilizer on typical smooth, nonsmooth, and discontinuous wavefronts defined on a regular grid is given. The results of the method’s performance on irregular grids and with partially missing data are analyzed, leading to the conclusion about its effectiveness in handling such data.

Penulis (4)

T

T. E. Romanenko

A

A. V. Razgulin

N

N. G. Iroshnikov

A

A. V. Larichev

Format Sitasi

Romanenko, T.E., Razgulin, A.V., Iroshnikov, N.G., Larichev, A.V. (2025). Wavefront Reconstruction by its Slopes via Physics-Informed Neural Networks. https://doi.org/10.5194/isprs-archives-XLVIII-2-W9-2025-233-2025

Akses Cepat

Informasi Jurnal
Tahun Terbit
2025
Sumber Database
DOAJ
DOI
10.5194/isprs-archives-XLVIII-2-W9-2025-233-2025
Akses
Open Access ✓