A simple convolutional autoencoder reconstructs planetary images with up to 99% pixel loss, and the author argues its latent space could be a more efficient data product than raw imagery.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.EP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The model is the message: Lightweight convolutional autoencoders applied to noisy imaging data for planetary science and astrobiology
A simple convolutional autoencoder reconstructs planetary images with up to 99% pixel loss, and the author argues its latent space could be a more efficient data product than raw imagery.