POLARIS is a new exoplanet imaging benchmark combining archival SPHERE/IRDIS polarimetric data with machine learning baselines, including a diffusion-enhanced contrastive method that classifies disk versus reference images with up to 93% accuracy.
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
-
POLARIS: A High-contrast Polarimetric Imaging Benchmark Dataset for Exoplanetary Disk Representation Learning
POLARIS is a new exoplanet imaging benchmark combining archival SPHERE/IRDIS polarimetric data with machine learning baselines, including a diffusion-enhanced contrastive method that classifies disk versus reference images with up to 93% accuracy.