Deep CosmoStat Days

Session

Source Separation

17 janv. 2025, 10:00

Cassini (CEA/DAp)

1. Single-channel source separation in wide-field astronomical imaging

Emmanuel Bertin (CEA Saclay)

17/01/2025 10:00

Wide-field astronomical images contain a mixture of overlapping sources from very different natures, including stars, galaxies, diffuse emission, and artifacts, complicating scientific analyses. Single-channel source separation methods based on deep learning offer a direct and powerful approach to disentangle these components using only individual observations. In this presentation I will...

9. Component Separation

Victor Bonjean Sia Gkokou

17/01/2025 10:30

10. SPT Component Separation Challenges

Cail Daley (CEA)

17/01/2025 10:55

15. Interpretable and scalable deep learning methods for blind source separation

Christophe Kervazo

17/01/2025 11:20