Accelerating Multiframe Blind Deconvolution via Deep Learning

Asensio Ramos, Andrés; Esteban Pozuelo, Sara; Kuckein, Christoph
Bibliographical reference

Solar Physics

Advertised on:
Number of authors
IAC number of authors
Refereed citations
Ground-based solar-image restoration is a computationally expensive procedure that involves nonlinear optimization techniques. The presence of atmospheric turbulence produces perturbations in individual images that make it necessary to apply blind deconvolution techniques. These techniques rely on the observation of many short-exposure frames that are used to simultaneously infer the instantaneous state of the atmosphere and the unperturbed object. We have recently explored the use of machine learning to accelerate this process, with promising results. We build upon this previous work to propose several interesting improvements that lead to better models. Also, we propose a new method to accelerate the restoration based on algorithm unrolling. In this method, the image-restoration problem is solved with a gradient-descent method that is unrolled and accelerated, aided by a few small neural networks. The role of the neural networks is to correct the estimation of the solution at each iterative step. The model is trained to perform the optimization in a small fixed number of steps with a curated dataset. Our findings demonstrate that both methods significantly reduce the restoration time compared to the standard optimization procedure. Furthermore, we showcase that these models can be trained in an unsupervised manner using observed images from three different instruments. Remarkably, they also exhibit robust generalization capabilities when applied to new datasets. To foster further research and collaboration, we openly provide the trained models, along with the corresponding training and evaluation code, as well as the training dataset, to the scientific community.
Related projects
Project Image
Magnetism, Polarization and Radiative Transfer in Astrophysics
Magnetic fields pervade all astrophysical plasmas and govern most of the variability in the Universe at intermediate time scales. They are present in stars across the whole Hertzsprung-Russell diagram, in galaxies, and even perhaps in the intergalactic medium. Polarized light provides the most reliable source of information at our disposal for the
Tanausú del
Pino Alemán
Project Image
Solar and Stellar Magnetism
Magnetic fields are at the base of star formation and stellar structure and evolution. When stars are born, magnetic fields brake the rotation during the collapse of the mollecular cloud. In the end of the life of a star, magnetic fields can play a key role in the form of the strong winds that lead to the last stages of stellar evolution. During
Felipe García