English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Supervised training has led to state-of-the-art results in image and videodenoising. However, its application to real data is limited since it requireslarge datasets of noisy-clean pairs that are difficult to obtain. For thisreason, networks are often trained on realistic synthetic data. More recently,some self-supervised frameworks have been proposed for training such denoisingnetworks directly on the noisy data without requiring ground truth. Onsynthetic denoising problems supervised training outperforms self-supervisedapproaches, however in recent years the gap has become narrower, especially forvideo. In this paper, we propose a study aiming to determine which is the bestapproach to train denoising networks for real raw videos: supervision onsynthetic realistic data or self-supervision on real data. A complete studywith quantitative results in case of natural videos with real motion isimpossible since no dataset with clean-noisy pairs exists. We address thisissue by considering three independent experiments in which we compare the twoframeworks. We found that self-supervision on the real data outperformssupervision on synthetic data, and that in normal illumination conditions thedrop in performance is due to the synthetic ground truth generation, not thenoise model.

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