Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

Open Denoising: An Open Benchmark for Image Denoising Methods

This repository stores the code of OpenDenoising. A comparative study built using OpenDenoising and accespted at ICASSP 2020 can be found at: OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers, F. Lemarchand, E. Fernandes-Montesuma, M. Pelcat and E. Nogues https://arxiv.org/abs/1910.08328

Contributors

Repository organization

  • Documentation contains the code documentation, hosted at Read The Docs website.
  • OpenDenoising contains the code for the OpenDenoising benchmark. It is divided into four modules,
    • data It contains an interface for dataset generator classes that will feed data into the denoiser models.
    • model It contains various interfaces defining the behaviour of Deep Learning denoising models, and Filtering models. It has also a series of Wrapper Classes, designed to implement these interfaces using each Framework.
    • benchmarking It contains the functions responsable for evaluation and visualization of model's performance.
    • custom_callbacks It contains the functions responsable for tracking the training of Deep Learning models.

Here is an overview of the layers of abstraction in our Benchmark:

Class diagram

For a better visualisation of how the Benchmark classes are organized, we provide an UML Class diagram:

Built-in models

Filtering models

  • BM3D1 [Matlab Code]. By using BM3D you are agreeing with its license terms

Deep Learning models

References

  1. Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Transactions on image processing. 2007
  2. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing. 2017
  3. Kligvasser I, Rott Shaham T, Michaeli T. xUnit: Learning a spatial activation function for efficient image restoration. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018
  4. Mao XJ, Shen C, Yang YB. Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv preprint arXiv:1606.08921. 2016
  5. Liu P, Zhang H, Lian W, Zuo W. Multi-Level Wavelet Convolutional Neural Networks. IEEE Access. 2019
  6. Liu P, Zhang H, Zhang K, Lin L, Zuo W. Multi-level wavelet-CNN for image restoration. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2018
  7. Krull, A., Buchholz, T. O., & Jug, F. (2019). Noise2void-learning denoising from single noisy images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

Contributing

If you want to contribute or make a suggestion to this Benchmark, you can either do so by contacting us, or by using git pull requests/issues tools.

Giving Credit

If using material of this repository for publication please cite us using this bibtex: @article{lemarchand2019opendenoising, title={OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers}, author={Lemarchand, Florian and Montesuma, Eduardo Fernandes and Pelcat, Maxime and Nogues, Erwan}, journal={arXiv preprint arXiv:1910.08328}, year={2019} }

About

An Open Source Benchmark for Evaluating Image Denoising Algorithms

Resources

License

Releases

No releases published

Packages

No packages published