torchmfbd: A flexible multi-object, multi-frame blind deconvolution code

¹ Instituto de Astrofísica de Canarias (IAC), Avda Vía Láctea S/N, 38200 La Laguna, Tenerife, Spain
² Departamento de Astrofísica, Universidad de La Laguna, 38205 La Laguna, Tenerife, Spain
³ Institute for Solar Physics, Dept. of Astronomy, Stockholm University, AlbaNova University Centre, 10691 Stockholm, Sweden
⁴ Institute of Theoretical Astrophysics, University of Oslo, PO Box 1029 Blindern, 0315 Oslo, Norway
⁵ Rosseland Centre for Solar Physics, University of Oslo, PO Box 1029 Blindern, 0315 Oslo, Norway

^★ Corresponding author: andres.asensio@iac.es

Received: 15 May 2025
Accepted: 24 September 2025

Abstract

Context. Post-facto image restoration techniques are essential for improving the quality of ground-based astronomical observations, which are affected by atmospheric turbulence. Multi-object, multi-frame blind deconvolution (MOMFBD) methods are widely used in solar physics to achieve diffraction-limited imaging.

Aims. We present torchmfbd, a new open-source code for MOMFBD that leverages the PyTorch library to provide a flexible, GPU-accelerated framework for image restoration. The code is designed to handle spatially variant point spread functions (PSFs) and includes advanced regularization techniques.

Methods. The code implements the MOMFBD method using a maximum a posteriori estimation framework. It supports both wavefront-based and data-driven PSF parameterizations, including a novel experimental approach using nonnegative matrix factorization. Regularization techniques, such as smoothness and sparsity constraints, can be incorporated to stabilize the solution. The code also supports dividing large fields of view into patches and includes tools for apodization and destretching. The code architecture is designed to become a flexible platform over which new reconstruction and regularization methods can also be straightforwardly implemented.

Results. We demonstrate the capabilities of torchmfbd on real solar observations, showing its ability to produce high-quality reconstructions efficiently. The GPU acceleration significantly reduces computation time, making the code suitable for large datasets.