Paper Info
Title
GPU-based multigrid: real-time performance in high resolution nonlinear image processing
Abstract
Multigrid methods provide fast solvers for a wide variety of problems encountered in computer vision. Recent graphics hardware is ideally suited for the implementation of such methods, but this potential has not yet been fully realized. Typically, work in that area focuses on linear systems only, or on implementation of numerical solvers that are not as efficient as multigrid methods. We demonstrate that nonlinear multigrid methods can be used to great effect on modern graphics hardware. Specifically, we implement two applications: a nonlinear denoising filter and a solver for variational optical flow. We show that performing these computations on graphics hardware is between one and two orders of magnitude faster than comparable CPU-based implementations.
Year
DOI
Venue
2008
10.1007/978-3-540-79547-6_14
ICVS
Keywords
Field
DocType
recent graphics hardware,computer vision,gpu-based multigrid,comparable cpu-based implementation,modern graphics hardware,nonlinear multigrid method,numerical solvers,nonlinear denoising filter,fast solvers,multigrid method,graphics hardware,high resolution nonlinear image,real-time performance,linear system,partial differential equation,high resolution,partial differential equations,image processing,real time,gpgpu,optical flow
Nonlinear system,Graphics hardware,Linear system,Computer science,Computational science,General-purpose computing on graphics processing units,Solver,Optical flow,Multigrid method,Computation
Conference
Volume
ISSN
ISBN
5008
0302-9743
3-540-79546-4
Citations 
PageRank 
References 
11
0.90
11
Authors
2
Name
Order
Citations
PageRank
Harald Grossauer1412.43
Peter Thoman27913.20