# ViDeNN: Deep Blind Video Denoising

## TL;DR

ViDeNN is a deep learning model for blind video denoising that effectively combines spatial and temporal information without prior noise knowledge, handling various challenging conditions.

## Contribution

It introduces a CNN architecture that jointly denoises spatial frames and integrates temporal data, along with a specialized dataset for low-light training.

## Key findings

- Achieves results comparable to state-of-the-art methods
- Demonstrates effectiveness in low-light and dynamic scenes
- Validates the importance of training data quality

## Abstract

We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising). The CNN architecture uses a combination of spatial and temporal filtering, learning to spatially denoise the frames first and at the same time how to combine their temporal information, handling objects motion, brightness changes, low-light conditions and temporal inconsistencies. We demonstrate the importance of the data used for CNNs training, creating for this purpose a specific dataset for low-light conditions. We test ViDeNN on common benchmarks and on self-collected data, achieving good results comparable with the state-of-the-art.