Abstract | ||
---|---|---|
•We formulate a multi-resolution NMF problem for any β-divergence.•We propose a novel algorithm based on the multiplicative updates (MU).•We apply, for the first time, such a model to the blind unmixing of audio spectrograms.•We apply our model for the hyper/multi-spectral image super-resolution problem.•Our MU outperform state-of-the-art algorithms in the presence of non-Gaussian noise. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.sigpro.2021.108428 | Signal Processing |
Keywords | DocType | Volume |
Blind spectral unmixing,Nonnegative matrix factorization,β-divergences,Multiplicative updates,Hyperspectral and multispectral image fusion | Journal | 193 |
ISSN | Citations | PageRank |
0165-1684 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Valentin Leplat | 1 | 0 | 0.34 |
Nicolas Gillis | 2 | 503 | 39.77 |
Cédric Févotte | 3 | 2380 | 149.37 |