Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Frontiers Media SA 2020-02-19

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.

denoising; CARE; deep learning; microscopy data; probabilistic

Open access content. Open access content
http://creativecommons.org/licenses/by/4.0
openAccess
http://www.sherpa.ac.uk/romeo/issn/2624-9898
Creative Commons Attribution 4.0 International

5
2
English

CZBUT oai:dspace.vutbr.cz:11012/193231
Frontiers in Computer Science. 2020, vol. 2, issue 5, p. 1-9.
2624-9898
159778
10.3389/fcomp.2020.00005
1197600549

BRNO UNIV OF TECHNOL
From OAIster®, provided by the OCLC Cooperative.

edsoai.on1197600549