Deep learning image burst stacking to reconstruct high-resolution ground-based solar observations

TL;DR

This paper presents a deep learning method for real-time high-resolution solar imaging by stacking short exposure images, outperforming traditional techniques especially under challenging atmospheric conditions.

Contribution

The authors introduce a novel unpaired image translation model that reconstructs high-quality solar images from image bursts, improving robustness and efficiency over existing methods.

Findings

Enhanced perceptual quality in reconstructed images

Robustness to artifacts in speckle reconstructions

Optimal results with full image burst input

Abstract

Large aperture ground based solar telescopes allow the solar atmosphere to be resolved in unprecedented detail. However, observations are limited by Earths turbulent atmosphere, requiring post image corrections. Current reconstruction methods using short exposure bursts face challenges with strong turbulence and high computational costs. We introduce a deep learning approach that reconstructs 100 short exposure images into one high quality image in real time. Using unpaired image to image translation, our model is trained on degraded bursts with speckle reconstructions as references, improving robustness and generalization. Our method shows an improved robustness in terms of perceptual quality, especially when speckle reconstructions show artifacts. An evaluation with a varying number of images per burst demonstrates that our method makes efficient use of the combined image information and achieves the best reconstructions when provided with the full image burst.