A4 Conference proceedings

Blind Hierarchical Deconvolution

Open Access publication

Publication Details
Authors: Arjas Arttu, Roininen Lassi, Sillanpää Mikko J, Hauptmann Andreas
Publication year: 2020
Language: English
Related Journal or Series Information: IEEE International Workshop On Machine Learning For Signal Processing
Title of parent publication: 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP)
Journal acronym: MLSP
ISBN: 978-1-7281-6663-6
eISBN: 978-1-7281-6662-9
ISSN: 2161-0363
eISSN: 2161-0371
JUFO-Level of this publication: 1
Open Access: Open Access publication
Location of the parallel saved publication: https://arxiv.org/abs/2007.11391


Deconvolution is a fundamental inverse problem in signal processing and the prototypical model for recovering a signal from its noisy measurement. Nevertheless, the majority of model-based inversion techniques require knowledge on the convolution kernel to recover an accurate reconstruction and additionally prior assumptions on the regularity of the signal are needed. To overcome these limitations, we parametrise the convolution kernel and prior length-scales, which are then jointly estimated in the inversion procedure. The proposed framework of blind hierarchical deconvolution enables accurate reconstructions of functions with varying regularity and unknown kernel size and can be solved efficiently with an empirical Bayes two-step procedure, where hyperparameters are first estimated by optimisation and other unknowns then by an analytical formula.

Last updated on 2020-09-11 at 11:10