An Analysis and Implementation of the FFDNet Image Denoising Method

Matias Tassano , Julie Delon (1) , Thomas Veit (2)

1 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5
2 LIVIC - Laboratoire sur les Interactions Véhicules-Infrastructure-Conducteurs

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 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.

Domaines: Traitement des images [eess.IV]

Matias Tassano, Julie Delon, Thomas Veit. An Analysis and Implementation of the FFDNet Image Denoising Method. Image Processing On Line, 2019, 9, pp.1-25. ⟨10.5201/ipol.2019.231⟩. ⟨hal-02002837⟩