Unsupervised Deep Video Denoising

TL;DR

This paper introduces UDVD, an unsupervised deep learning method for video denoising that trains solely on noisy data, achieving performance comparable to supervised methods without requiring motion compensation.

Contribution

The paper presents a novel CNN architecture for unsupervised video denoising that adapts to local motion without explicit motion compensation, trained only on noisy videos.

Findings

UDVD performs comparably to supervised state-of-the-art methods.

It effectively denoises real-world microscopy videos.

It automatically adapts to local motion in noisy videos.

Abstract

Deep convolutional neural networks (CNNs) for video denoising are typically trained with supervision, assuming the availability of clean videos. However, in many applications, such as microscopy, noiseless videos are not available. To address this, we propose an Unsupervised Deep Video Denoiser (UDVD), a CNN architecture designed to be trained exclusively with noisy data. The performance of UDVD is comparable to the supervised state-of-the-art, even when trained only on a single short noisy video. We demonstrate the promise of our approach in real-world imaging applications by denoising raw video, fluorescence-microscopy and electron-microscopy data. In contrast to many current approaches to video denoising, UDVD does not require explicit motion compensation. This is advantageous because motion compensation is computationally expensive, and can be unreliable when the input data are noisy. A gradient-based analysis reveals that UDVD automatically adapts to local motion in the input noisy videos. Thus, the network learns to perform implicit motion compensation, even though it is only trained for denoising.