napari-n2v

A self-supervised denoising algorithm now usable by all in napari.

<img src="https://raw.githubusercontent.com/juglab/napari-n2v/master/docs/images/noisy_denoised.png" width="800" /> ----------------------------------

Installation

Check out the documentation for more detailed installation instructions.

You can then start the napari plugin by clicking on "Plugins > napari_n2v > Training", or run the plugin directly from a script.

Quick demo

You can try out a demo by loading the N2V Demo prediction plugin and directly clicking on Predict. This model was trained using the N2V2 example.

<img src="https://raw.githubusercontent.com/juglab/napari-n2v/master/docs/images/demo.gif" width="800" />

Documentation

Documentation is available on the project website.

Contributing and feedback

Contributions are very welcome. Tests can be run with tox, please ensure the coverage at least stays the same before you submit a pull request. You can also help us improve by filing an issue along with a detailed description or contact us through the image.sc forum (tag @jdeschamps).

Citations

N2V

Alexander Krull, Tim-Oliver Buchholz, and Florian Jug. "Noise2void-learning denoising from single noisy images." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019.

structN2V

Coleman Broaddus, et al. "Removing structured noise with self-supervised blind-spot networks." 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE, 2020.

N2V2

Eva Hoeck, Tim-Oliver Buchholz, et al. "N2V2 - Fixing Noise2Void Checkerboard Artifacts with Modified Sampling Strategies and a Tweaked Network Architecture", arXiv (2022).

Acknowledgements

This plugin was developed thanks to the support of the Silicon Valley Community Foundation (SCVF) and the Chan-Zuckerberg Initiative (CZI) with the napari Plugin Accelerator grant 2021-240383.

Distributed under the terms of the BSD-3 license, "napari-n2v" is a free and open source software.