Unsupervised Deep Video Denoising
This work is significant for researchers and practitioners in fields like microscopy where obtaining clean video data for supervised training is often impossible, enabling the use of deep learning for denoising in these challenging scenarios.
The paper proposes an Unsupervised Deep Video Denoiser (UDVD), a CNN that can be trained solely on noisy video data, addressing the common problem of unavailable clean videos in applications like microscopy. UDVD achieves performance comparable to supervised state-of-the-art methods, even when trained on a single short noisy video.
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.