An Analysis and Implementation of the FFDNet Image Denoising Method
Matias Tassano, Julie Delon, Thomas Veit
→ BibTeX
@article{ipol.2019.231,
    title   = {{An Analysis and Implementation of the FFDNet Image Denoising Method}},
    author  = {Tassano, Matias and Delon, Julie and Veit, Thomas},
    journal = {{Image Processing On Line}},
    volume  = {9},
    pages   = {1--25},
    year    = {2019},
    doi     = {10.5201/ipol.2019.231},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2019.231}}
published
2019-01-06
reference
Matias Tassano, Julie Delon, and Thomas Veit, An Analysis and Implementation of the FFDNet Image Denoising Method, Image Processing On Line, 9 (2019), pp. 1–25. https://doi.org/10.5201/ipol.2019.231

Communicated by Gabriele Facciolo
Demo edited by Gabriele Facciolo

Abstract

FFDNet is a recent image denoising method based on a convolutional neural network architecture. In contrast to other existing neural network denoisers, FFDNet exhibits several desirable properties such as faster execution time and smaller memory footprint, and the ability to handle a wide range of noise levels effectively with a single network model. The combination between its denoising performance and lower computational load makes this algorithm attractive for practical denoising applications. In this paper we propose an open-source implementation of the method based on PyTorch, a popular machine learning library for Python. Code for the training of the network is also provided. We also discuss the characteristics of the architecture of this algorithm and we compare it to other similar methods.

Download