EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Point spread function deconvolution using a convolutional autoencoder

Sreevarsha Sreejith, Anže Slosar, Hong Wang

Physical Review D · 21.11.2024 · 110 (10)

DOI: 10.1103/physrevd.110.103030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review D, online erschienen am 21.11.2024. Verfasst von Sreevarsha Sreejith und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A major issue in optical astronomical image analysis is the combined effect of the instrument’s point spread function (PSF) and the atmospheric seeing that blurs images and changes their shape in a way that is band and time-of-observation dependent. In this work we present a very simple neural network based approach to nonblind image deconvolution that relies on feeding a convolutional autoencoder (CAE) input images that have been preprocessed by convolution with the corresponding PSF and its regularized inverse, a method which is both conceptually simple and computationally less intensive. We also present here, a new approach for dealing with limited input dynamic range of neural networks compared to the dynamic range present in astronomical images. Published by the American Physical Society 2024

Zitieren

APA

Sreejith, S., Slosar, A., & Wang, H. (2024). Point spread function deconvolution using a convolutional autoencoder. Physical Review D, 110(10). https://doi.org/10.1103/physrevd.110.103030

Vancouver

Sreejith S, Slosar A, Wang H. Point spread function deconvolution using a convolutional autoencoder. Physical Review D. 2024;110(10). doi:10.1103/physrevd.110.103030

BibTeX
@article{Sreejith2024,
  author = {Sreejith, Sreevarsha and Slosar, Anže and Wang, Hong},
  title = {Point spread function deconvolution using a convolutional autoencoder},
  journal = {Physical Review D},
  year = {2024},
  volume = {110},
  number = {10},
  doi = {10.1103/physrevd.110.103030}
}
Kostenlos starten →