Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DVDnet: A Fast Network for Deep Video Denoising

About

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 denoising 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 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. The experiments show that our algorithm compares favorably to other state-of-art methods. Video examples, code and models are publicly available at \url{https://github.com/m-tassano/dvdnet}.

Matias Tassano, Julie Delon, Thomas Veit• 2019

Related benchmarks

TaskDatasetResultRank
Video DenoisingSet8
PSNR36.08
136
Video DenoisingSet8 (test)
PSNR36.08
127
Video DenoisingDAVIS
PSNR38.13
79
Video DenoisingDAVIS 2017 (test)
PSNR38.13
60
Video DenoisingDAVIS 2017
PSNR38.13
51
Video DenoisingDAVIS (test)
PSNR38.13
37
Video DenoisingIOCV 10 (full)
PSNR38.53
13
Video DenoisingCRVD 87 (full)
PSNR34.5
13
Video DenoisingSet8 960x540 resolution (test)
Inference Time (s)8
4
Showing 9 of 9 rows

Other info

Code

Follow for update