DVDNET: A FAST NETWORK FOR DEEP VIDEO DENOISING

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

1 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5
2 GoPro Technology France

In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Previous neural network based approaches to video denois-ing have been unsuccessful as their performance cannot compete with the performance of patch-based methods. However, our approach outperforms other patch-based competitors with significantly lower computing times. In contrast to other existing neural network denoisers, our algorithm exhibits several desirable properties such as a small memory footprint, and the ability to handle a wide range of noise levels with a single network model. The combination between its denois-ing performance and lower computational load makes this algorithm attractive for practical denoising applications. We compare our method with different state-of-art algorithms, both visually and with respect to objective quality metrics. The experiments show that our algorithm compares favorably to other state-of-art methods. Video examples, code and models are publicly available at https://github.com/ m-tassano/dvdnet.

Mots clés: video denoising; CNN; residual learning; neural networks; image restoration

Domaines: Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]

Matias Tassano, Julie Delon, Thomas Veit. DVDNET: A FAST NETWORK FOR DEEP VIDEO DENOISING. 2019 IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. ⟨hal-02147604⟩