Restoration of images with a spatially varying PSF of the T80-S telescope optical model using neural networks

Most image restoration methods in astronomy rely upon probabilistic tools that infer the best solution for a deconvolution problem. They achieve good performances when the point spread function (PSF) is spatially invariant in the image plane. However, this condition is not always satisfied in real optical systems. We propose a new method for the restoration of images affected by static and anisotropic aberrations using Deep Neural Networks that can be directly applied to sky images. The network is trained using simulated sky images corresponding to the T80-S Telescope optical model, a 80-cm survey imager at Cerro Tololo (Chile), which are synthesized using a Zernike polynomial representation of the optical system. Once trained, the network can be used directly on sky images, outputting a corrected version of the image that has a constant and known PSF across its field of view. The method is to be tested on the T80-S Telescope. We present the method and results on synthetic data.