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

## TL;DR

FastDVDnet is a real-time deep video denoising algorithm that achieves high performance without flow estimation, offering fast runtimes and versatility across noise levels, suitable for practical applications.

## Contribution

Introduces FastDVDnet, a neural network-based video denoising method that outperforms existing neural approaches in speed and versatility without requiring motion compensation.

## Key findings

- Achieves comparable or better denoising quality than state-of-the-art methods.
- Operates significantly faster than previous neural network denoisers.
- Handles a wide range of noise levels with a single model.

## 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 runtimes, 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.