Published on:
8 May 2024
Primary Category:
Instrumentation and Methods for Astrophysics
Paper Authors:
Spencer Bialek,
Emmanuel Bertin,
Sébastien Fabbro,
Hervé Bouy,
Jean-Pierre Rivet,
Olivier Lai,
Jean-Charles Cuillandre
Uses neural network to reconstruct sharp images from turbulent video
Trained on simulated images with annotated ground truth
Works on wide-field images by splitting into tiles
Accurately associates speckles to sources across seeing range
Gives much clearer images without flux or astrometric issues
Atmospheric turbulence mitigation in wide-field images
This paper introduces a new technique to remove the effects of atmospheric turbulence from wide-field astronomical images. It uses a neural network trained on simulated data that takes in a sequence of short-exposure images of a star field and reconstructs a single sharp, noiseless image. Across different levels of atmospheric seeing, it accurately associates speckles with their source stars and separates light from neighboring stars. This gives much clearer images without compromising astrometric stability or flux measurements.
Demystifying the twinkling stars: A clear guide to sharpening our view of the night sky
Removing noise from low-light images
Removing distortion in videos using deep learning
Automated detection of transients in images from the 4m ILMT
Object segmentation in turbulent video
Training a neural network to remove multiple noise types
No comments yet, be the first to start the conversation...
Sign up to comment on this paper