DVDNET: A FAST NETWORK FOR DEEP VIDEO DENOISING

Abstract : 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.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02147604
Contributor : Matias Tassano <>
Submitted on : Tuesday, June 4, 2019 - 5:50:41 PM
Last modification on : Monday, July 1, 2019 - 3:14:03 PM

File

article_icip2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02147604, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

88

Files downloads

90