FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation

1 Jul 2019Matias TassanoJulie DelonThomas Veit

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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Video Denoising DAVIS sigma10 FastDVDnet PSNR 38.97 # 1
Video Denoising DAVIS sigma20 FastDVDnet PSNR 35.86 # 1
Video Denoising DAVIS sigma30 FastDVDnet PSNR 34.06 # 2
Video Denoising DAVIS sigma40 FastDVDnet PSNR 32.8 # 2
Video Denoising DAVIS sigma50 FastDVDnet PSNR 31.83 # 2
Video Denoising Set8 sigma10 FastDVDnet PSNR 36.43 # 1
Video Denoising Set8 sigma20 FastDVDnet PSNR 33.37 # 2
Video Denoising Set8 sigma30 FastDVDnet PSNR 31.6 # 2
Video Denoising Set8 sigma40 FastDVDnet PSNR 30.37 # 2
Video Denoising Set8 sigma50 FastDVDnet PSNR 29.42 # 2