GPU-Accelerated Denoising in 3D (GD3D)
Abstract
The raw computational power GPU Accelerators enables fast denoising of 3D MR images using bilateral filtering, anisotropic diffusion, and non-local means. This software addresses two facets of this promising application: what tuning is necessary to achieve optimal performance on a modern GPU? And what parameters yield the best denoising results in practice? To answer the first question, the software performs an autotuning step to empirically determine optimal memory blocking on the GPU. To answer the second, it performs a sweep of algorithm parameters to determine the combination that best reduces the mean squared error relative to a noiseless reference image.
- Developers:
- Release Date:
- Project Type:
- Open Source, No Publicly Available Repository
- Software Type:
- Scientific
- Licenses:
- Other
- Sponsoring Org.:
- USDOEPrimary Award/Contract Number:AC02-05CH11231
- Code ID:
- 57176
- Site Accession Number:
- 5335; 2014-002
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Country of Origin:
- United States
Citation Formats
Howison, Mark, Bethehl, E. Wes, and USDOE. GPU-Accelerated Denoising in 3D (GD3D).
Computer software. https://www.osti.gov//servlets/purl/1231920. USDOE. 1 Oct. 2013.
Web. doi:10.11578/dc.20210521.68.
Howison, Mark, Bethehl, E. Wes, & USDOE. (2013, October 1). GPU-Accelerated Denoising in 3D (GD3D) [Computer software]. https://www.osti.gov//servlets/purl/1231920. https://doi.org/10.11578/dc.20210521.68
Howison, Mark, Bethehl, E. Wes, and USDOE. GPU-Accelerated Denoising in 3D (GD3D).
Computer software. October 1, 2013. https://www.osti.gov//servlets/purl/1231920. doi:https://doi.org/10.11578/dc.20210521.68.
@misc{osti_1231920,
title = {GPU-Accelerated Denoising in 3D (GD3D)},
author = {Howison, Mark and Bethehl, E. Wes and USDOE},
abstractNote = {The raw computational power GPU Accelerators enables fast denoising of 3D MR images using bilateral filtering, anisotropic diffusion, and non-local means. This software addresses two facets of this promising application: what tuning is necessary to achieve optimal performance on a modern GPU? And what parameters yield the best denoising results in practice? To answer the first question, the software performs an autotuning step to empirically determine optimal memory blocking on the GPU. To answer the second, it performs a sweep of algorithm parameters to determine the combination that best reduces the mean squared error relative to a noiseless reference image.},
url = {https://www.osti.gov//servlets/purl/1231920},
doi = {10.11578/dc.20210521.68},
url = {https://www.osti.gov/biblio/1231920},
year = {Tue Oct 01 00:00:00 EDT 2013},
month = {Tue Oct 01 00:00:00 EDT 2013},
note =
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.