English

Lightweight Video Denoising Using a Classic Bayesian Backbone

Image and Video Processing 2024-08-08 v1 Artificial Intelligence Computer Vision and Pattern Recognition Signal Processing

Abstract

In recent years, state-of-the-art image and video denoising networks have become increasingly large, requiring millions of trainable parameters to achieve best-in-class performance. Improved denoising quality has come at the cost of denoising speed, where modern transformer networks are far slower to run than smaller denoising networks such as FastDVDnet and classic Bayesian denoisers such as the Wiener filter. In this paper, we implement a hybrid Wiener filter which leverages small ancillary networks to increase the original denoiser performance, while retaining fast denoising speeds. These networks are used to refine the Wiener coring estimate, optimise windowing functions and estimate the unknown noise profile. Using these methods, we outperform several popular denoisers and remain within 0.2 dB, on average, of the popular VRT transformer. Our method was found to be over x10 faster than the transformer method, with a far lower parameter cost.

Keywords

Cite

@article{arxiv.2408.03904,
  title  = {Lightweight Video Denoising Using a Classic Bayesian Backbone},
  author = {Clément Bled and François Pitié},
  journal= {arXiv preprint arXiv:2408.03904},
  year   = {2024}
}

Comments

Paper accepted to ICME 2024

R2 v1 2026-06-28T18:06:45.002Z