3D Non-Local Means denoising via multi-GPU

Giuseppe Palma, Francesco Piccialli, Pasquale De Michele, Salvatore Cuomo, Marco Comerci, Pasquale Borrelli, Bruno Alfano
Inst. of Biostructures and Bioimaging, National Research Council of Italy, Via De Amicis 95, 80145 Naples, Italy
Federated Conference on Computer Science and Information Systems, 2013


   title={3D Non-Local Means denoising via multi-GPU},

   author={Palma, Giuseppe and Comerci, Marco and Alfano, Bruno and Cuomo, Salvatore and De Michele, Pasquale and Piccialli, Francesco and Borrelli, Pasquale},



Download Download (PDF)   View View   Source Source   



Non-Local Means (NLM) algorithm is widely considered as a state-of-the-art denoising filter in many research fields. High computational complexity led to implementations on Graphic Processor Unit (GPU) architectures, which achieve reasonable running times by filtering, slice-by-slice, 3D datasets with a 2D NLM approach. Here we present a fully 3D NLM implementation on a multi-GPU architecture and suggest its high scalability. The performance results we discuss encourage the coding of further filter improvements and the investigation of a large spectrum of applicative scenarios.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: