High-Dimensional Mixture Models For Unsupervised Image DenoisingMS14

I will address the problem of patch-based image denoising through the unsupervised learning of a high-dimensional mixture model on the noisy patches. To overcome the curse of dimensionality, our model adopts a parsimonious modeling which assumes that the patches live in group-specific subspaces of low dimensionalities. This yields a numerically stable blind denoising algorithm that demonstrates state-of-the-art performance, both when the noise level is known and unknown. Joint work with Charles Bouveyron and Antoine Houdard.

This presentation is part of Minisymposium “MS14 - Denoising in Photography and Video (2 parts)
organized by: Stacey Levine (Duquesne University) , Marcelo Bertalmío (University Pompeu Fabra) .

Julie Delon (Université Paris Descartes)
image enhancement, image reconstruction, inverse problems