FastDVDnet: Towards Real-Time Video Denoising Without Explicit Motion Estimation

Abstract : In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Until recently, video denoising with neural networks had been a largely under explored domain, and existing methods could not compete with the performance of the best patch-based methods. The approach we introduce in this paper, called FastDVDnet, shows similar or better performance than other state-of-the-art competitors with significantly lower computing times. In contrast to other existing neural network denoisers, our algorithm exhibits several desirable properties such as fast run-times, and the ability to handle a wide range of noise levels with a single network model. The characteristics of its architecture make it possible to avoid using a costly motion compensation stage while achieving excellent performance. The combination between its denoising 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.
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02170027
Contributor : Matias Tassano <>
Submitted on : Monday, July 1, 2019 - 4:15:30 PM
Last modification on : Thursday, July 4, 2019 - 3:58:06 AM

File

article_video.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02170027, version 1

Collections

Citation

Matias Tassano, Julie Delon, Thomas Veit. FastDVDnet: Towards Real-Time Video Denoising Without Explicit Motion Estimation. 2019. ⟨hal-02170027⟩

Share

Metrics

Record views

39

Files downloads

46