Accelerating Multiframe Blind Deconvolution via Deep Learning

Abstract

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. As well, 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.

arXiv comment26 pages, 9 figures, accepted for publication in Solar Physics

References in corpus (9)

• CRISP Spectropolarimetric Imaging of Penumbral Fine Structure
• Physical Properties of a Sunspot Chromosphere with Umbral Flashes
• Multi-frame blind deconvolution with linear equality constraints
• SSTRED: Data- and metadata-processing pipeline for CHROMIS and CRISP
• Stokes imaging polarimetry using image restoration at the Swedish 1-m Solar Telescope
• Real-time multiframe blind deconvolution of solar images
• GREGOR: Optics Redesign and Updates from 2018-2020
• Learning to do multiframe wavefront sensing unsupervisedly: applications to blind deconvolution
• sTools - a data reduction pipeline for the GREGOR Fabry-Pérot Interferometer and the High-resolution Fast Imager at the GREGOR solar telescope

Cited by in corpus (3)

• Instrument-To-Instrument translation: Instrumental advances drive restoration of solar observation series via deep learning
• Deep learning image burst stacking to reconstruct high-resolution ground-based solar observations
• Solar multi-object multi-frame blind deconvolution with a spatially variant convolution neural emulator