Astrophysical image separation using particle filters

In this work, we will confront the problem of source separation in the field of astrophysics, where the contributions of various Galactic and extra-Galactic components need to be separated from a set of observed noisy mixtures. Most of the previous work on the problem perform blind source separation, assume noiseless models, and in the few cases when noise is taken into account assume Gaussianity and space-invariance. However, in the real scenario both the sources and the noise are space-varying. In this work, we present a novel technique, namely particle filtering, for the non-blind (Bayesian) solution of the source separation problem, in case of non-stationary sources and noise, by exploiting available a-priori information.