Sorry, you need to enable JavaScript to visit this website.

Accelerated graph-based spectral polynomial filters

Citation Author(s):
Alexander Malyshev
Submitted by:
Andrew Knyazev
Last updated:
23 February 2016 - 1:44pm
Document Type:
Presentation Slides
Document Year:
2015
Event:
Presenters Name:
Alexander Malyshev

Abstract 

Abstract: 

Graph-based spectral denoising is a low-pass filtering using the eigendecomposition of the graph Laplacian matrix of a noisy signal. Polynomial filtering avoids costly computation of the eigendecomposition by projections onto suitable Krylov subspaces. Polynomial filters can be based, e.g., on the bilateral and guided filters. We propose constructing accelerated polynomial filters by running flexible Krylov subspace based linear and eigenvalue solvers such as the Block Locally Optimal Preconditioned Conjugate Gradient (LOBPCG) method. (arXiv:1509.02468 [cs.CV], DOI: 10.1109/MLSP.2015.7324315)

MLSP2015.pdf

PDF icon MLSP2015.pdf (733)
Media Folder: 
up
0 users have voted:

Dataset Files

MLSP2015.pdf

(733)