Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They are traditionally trained on pairs of images, which are often hard to obtain for practical applications. This motivates self-supervised training methods, such as Noise2Void (N2V) that operate on single noisy...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in computer science (Lausanne) Jg. 2
Hauptverfasser: Krull, Alexander, Vičar, Tomáš, Prakash, Mangal, Lalit, Manan, Jug, Florian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Frontiers Media S.A 19.02.2020
Schlagworte:
CARE
deep learning
denoising
microscopy data
probabilistic
ISSN:2624-9898, 2624-9898
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Today, Convolutional Neural Networks (CNNs) are the leading method for image denoising. They are traditionally trained on pairs of images, which are often hard to obtain for practical applications. This motivates self-supervised training methods, such as Noise2Void (N2V) that operate on single noisy images. Self-supervised methods are, unfortunately, not competitive with models trained on image pairs. Here, we present Probabilistic Noise2Void (PN2V), a method to train CNNs to predict per-pixel intensity distributions. Combining these with a suitable description of the noise, we obtain a complete probabilistic model for the noisy observations and true signal in every pixel. We evaluate PN2V on publicly available microscopy datasets, under a broad range of noise regimes, and achieve competitive results with respect to supervised state-of-the-art methods.
ISSN:2624-9898
2624-9898
DOI:10.3389/fcomp.2020.00005