Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU134052" target="_blank" >RIV/00216305:26220/20:PU134052 - isvavai.cz</a>

Result on the web

<a href="https://www.frontiersin.org/articles/10.3389/fcomp.2020.00005/full" target="_blank" >https://www.frontiersin.org/articles/10.3389/fcomp.2020.00005/full</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3389/fcomp.2020.00005" target="_blank" >10.3389/fcomp.2020.00005</a>

Result language

angličtina

Original language name

Probabilistic Noise2Void: Unsupervised Content-Aware Denoising

Original language description

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.

Czech name

—

Czech description

—

Type

J_ost - Miscellaneous article in a specialist periodical

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2020

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Frontiers in Computer Science

ISSN

2624-9898

e-ISSN

—

Volume of the periodical

2

Issue of the periodical within the volume

5

Country of publishing house

CH - SWITZERLAND

Number of pages

9

Pages from-to

1-9

UT code for WoS article

—

EID of the result in the Scopus database

—