Unsupervised Deep Video Denoising
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.
PDF Abstract ICCV 2021 PDF ICCV 2021 AbstractCode
DAVIS
CRVD
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Video Denoising | DAVIS sigma20 | UDVD | PSNR | 35.16 | # 7 | |
| Video Denoising | DAVIS sigma30 | UDVD | PSNR | 33.92 | # 7 | |
| Video Denoising | DAVIS sigma40 | UDVD | PSNR | 32.68 | # 8 | |
| Video Denoising | DAVIS sigma50 | UDVD | PSNR | 31.70 | # 8 | |
| Video Denoising | Set8 sigma20 | UDVD | PSNR | 33.36 | # 7 | |
| Video Denoising | Set8 sigma30 | UDVD | PSNR | 32.01 | # 5 | |
| Video Denoising | Set8 sigma40 | UDVD | PSNR | 30.82 | # 5 | |
| Video Denoising | Set8 sigma50 | UDVD | PSNR | 29.89 | # 5 |
