Home

Awesome

image

PyPI - Python Version Code style: black codecov DOI Downloads

Aydin is a user-friendly, feature-rich, and fast image denoising tool that provides a number of self-supervised, auto-tuned, and unsupervised image denoising algorithms. Aydin handles from the get-go n-dimensional array-structured images with an arbitrary number of batch dimensions, channel dimensions, and typically up to 4 spatio-temporal dimensions.

It comes with Aydin Studio a graphical user interface to easily experiment with all the different algorithms and parameters available, a command line interface to run large jobs on the terminal possibly on powerfull remote machines, and an API for custom coding and integration into your scripts and applications. More details and exhaustive explanations can be found in Aydin's documentation.

And, of course, a simplified napari plugin is in the works! Notebooks for running on Collab are also planned. The project is commercial-use-friendly if you specify pyside as your GUI backend.

Supported algorithms:

Currently Aydin supports two main families of denoisers: the first family consists of 'classical' denoising algorithms that leverage among other: frequency domain filtering, smoothness priors, low-rank representations, self-similarity, and more. The second family consists of algorithms that leverage machine learning approaches such as convolutional neural networks (CNN) or gradient boosting (GB). In the Noise2Self paper we show that it is possible to calibrate any parameterised denoising algorithm, from the few parameters of a classical algorithm to the millions of weights of a deep neural network. We leverage and extend these ideas in Aydin to provide a variety of auto-tuned and trained high-quality image denoisers. What this means is that for example, we can discover automatically the optimal parameters for non-local-means (NLM) denoising, or the best cut-off frequencies for a low-pass denoiser. These parameters are difficult to determine 'by-hand' but when auto-tuned we show (see use-cases) that you can get remarkable results even with simple 'classic' denoisers, and even be competitive against more complex and slower approaches such as deep-learning based denoisers that can also be prone to hallucination and 'copy-paste' effects. Importantly, our experience denoising many different kinds of images has shown that tehre is not a single 'silver-bullet' denoiser, different kinds of datasets require different approaches.
Here is the list of currently available methods:

Some methods actually do combine multiple ideas and so the classification above is not strict. We recommend trying first a good baseline denoiser such as the Butterworth denoiser. If unsatisfied with the result, and you have a powerful computer with a recent NVIDIA graphics card, then we recommend you try the Noise2Self-FGR-cb denoiser. For detailed use-cases check here.

We regularly come up with new approaches and ideas, there is just not enough time to write papers about all these ideas. This means that the best 'publication' for some of these novel algorithms is this repo itself, and so please be so kind as to cite this repo for any ideas that you would use or reuse. We have a long todo list of existing, modified, as well as original algorithms that we plan to add to Aydin in the next weeks and months. We will do so progressively as time allows. Stay tuned!

Documentation

Aydin's documentation can be found here.

Installation of Aydin Studio

We recommend that users that are not familiar with python start with our user-friendly UI. Download it for your operating system here:

<img src="https://user-images.githubusercontent.com/1870994/140653991-fb570f5a-bc6f-4afd-95b6-e36d05d1382d.png" width="200" > <img src="https://user-images.githubusercontent.com/1870994/140653995-5055e607-5226-4b76-8cc4-04de17d2811f.png" width="200" > <img src="https://user-images.githubusercontent.com/1870994/140653999-5f6368d9-3e82-4d10-9283-2359aa1464fa.png" width="200" >

The latest releases and standalone executables can be found here and detailed installation instructions of Aydin Studio for all three operating systems can be found here.

Installation of Aydin in Conda:

First download and install miniconda or anaconda.

Then create a conda environment to host aydin:

conda create -n aydin_env python=3.9

Activate the environment:

conda activate aydin_env

Install Aydin in the environment:

pip install aydin

CUDA dependencies:

If you have a NVIDIA CUDA Graphics card, you should install the CUDA toolkit:

conda install cudatoolkit

Mac specific dependencies:

For Macs (OSX) you first need to do:

brew install libomp

You can install Brew by following the instructions here.

Ubuntu/Linux specific dependencies:

If you encounter problems running Aydin in Ubuntu/linux, please install the following package:

sudo apt install libqt5x11extras5

How to run ?

Assuming that you have installed Aydin in an environment, you can:

Start Aydin Studio from the command line with:

aydin

Run the Command Line Interface (CLI) for denoising:

aydin denoise path/to/noisyimage

Get help on command line usage:

aydin -h

Recommended Operating System Versions

Linux: Ubuntu 18.04+

Windows: Windows 10

OSX: Mojave 10.14.6+

Recommended Hardware:

Recommended specifications are: at least 16 Gb of RAM, ideally 32 Gb, and more for very large images, a CPU with at least 4 cores, preferably 16 or more, and a recent NVIDIA graphics card such as a RTX series card. Older graphics cards could work but may cause trouble or be too slow. Aydin Studio's summary page gives an overview of the strengths and weaknesses of your machine, highlighting in red and orange items that might be problematic.

Known Issues:

Here are some issues that are being actively addressed and will be addressed asap:

Road Map:

Planned features:

Contributing

Feel free to check our contributing guideline first and start discussing your new ideas and feedback with us through issues.

Cite this repo

You can cite our work with: https://doi.org/10.5281/zenodo.5654826