Self-supervision versus synthetic datasets: which is the lesser evil in the context of video denoising?

by   Valéry Dewil, et al.

Supervised training has led to state-of-the-art results in image and video denoising. However, its application to real data is limited since it requires large datasets of noisy-clean pairs that are difficult to obtain. For this reason, networks are often trained on realistic synthetic data. More recently, some self-supervised frameworks have been proposed for training such denoising networks directly on the noisy data without requiring ground truth. On synthetic denoising problems supervised training outperforms self-supervised approaches, however in recent years the gap has become narrower, especially for video. In this paper, we propose a study aiming to determine which is the best approach to train denoising networks for real raw videos: supervision on synthetic realistic data or self-supervision on real data. A complete study with quantitative results in case of natural videos with real motion is impossible since no dataset with clean-noisy pairs exists. We address this issue by considering three independent experiments in which we compare the two frameworks. We found that self-supervision on the real data outperforms supervision on synthetic data, and that in normal illumination conditions the drop in performance is due to the synthetic ground truth generation, not the noise model.


page 2

page 6

page 7

page 8

page 13


Noise2Inpaint: Learning Referenceless Denoising by Inpainting Unrolling

Deep learning based image denoising methods have been recently popular d...

Unsupervised Deep Video Denoising

Deep convolutional neural networks (CNNs) currently achieve state-of-the...

Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty

Image demosaicking and denoising are the two key fundamental steps in di...

Few Clean Instances Help Denoising Distant Supervision

Existing distantly supervised relation extractors usually rely on noisy ...

RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset

In recent years, raw video denoising has garnered increased attention du...

One-Pot Multi-Frame Denoising

The performance of learning-based denoising largely depends on clean sup...

PVDD: A Practical Video Denoising Dataset with Real-World Dynamic Scenes

To facilitate video denoising research, we construct a compelling datase...

Please sign up or login with your details

Forgot password? Click here to reset