napari NLM

NLM (non local means) denoising

  • Martin Weigert

License BSD-3 PyPI Python Version tests codecov napari hub


GPU accelerated non local means (NLM) denoising plugin for napari (WIP)

  • currently only supports single-channel 2D or 3D images
  • requires a OpenCL capable GPU

Screenshot

Installation

You can install napari-nlm via [pip]:

pip install napari-nlm

Usage

  1. Open example image Open Sample > napari-nlm: noisy bricks
  2. Adjust parameters
    • sigma: denoising strength (the larger sigma, the greater the smoothing)
    • patch_radius: size of local patches, 2 or 3 is a good default
    • search_radius: size of search area around each pixel to find similar patches, 7-11 is a good default
  3. Denoise by pressing run

License

Distributed under the terms of the [BSD-3] license, "napari-nlm" is free and open source software

Version:

  • 0.0.4

Last updated:

  • 2022-07-26

First released:

  • 2022-07-25

License:

  • BSD-3-Clause

Supported data:

  • Information not submitted

Plugin type:

Open extension:

Save extension:

Python versions supported:

Operating system:

  • Information not submitted

Requirements:

  • numpy
  • magicgui
  • qtpy
  • pyopencl (==2022.1.5)
  • gputools
  • scikit-image
  • tox ; extra == 'testing'
  • pytest ; extra == 'testing'
  • pytest-cov ; extra == 'testing'
  • pytest-qt ; extra == 'testing'
  • napari ; extra == 'testing'
  • pyqt5 ; extra == 'testing'
Website by the napari team, original design by CZI. Go to napari main website.