Fast Nonlocal Means for MRI denoising

This is a fast and robust implementation of the popular Nonlocal Means for MRI-Rician denoising. It works by computing the non-local weights based on distances in a features space comprising the local mean value and gradients of the image.

It can reach an acceleration factor of 20x over the original implementation, with an improved performance for medium-low SNR images.

We use a bias correction step for Rician noise based on the well-known Conventional Approach.

This software can be compiled either as a Slicer module or a stand-alone:

For diffusion MRI volumes, see also:

Key words: nonlocal (non-local) means, NLM, C++, ITK

Execution Options

Download Now:


3D Slicer License
Development Status:
Intended Audience:
Natural Language:
Operating System:
Programming Language:
Supported Data Format:


build requires:
works well with: