Improving Blind Spot Denoising for Microscopy.

Goncharova, Anna; Honigmann, Alf; Jug, Florian; Krull, Alexander

doi:10.1007/978-3-030-66415-2_25

Local TagsRelease HistoryDetailsSummary

Improving Blind Spot Denoising for Microscopy.

Goncharova, A., Honigmann, A., Jug, F., & Krull, A. (2020). Improving Blind Spot Denoising for Microscopy. In A. Bartoli (Ed.), Computer vision - ECCV 2020 workshops: Glasgow, UK, August 23-28, 2020: proceedings: Part 1 (pp. 380-393). Cham: Springer International Publishing.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/21.11116/0000-000A-0C46-B Version Permalink: https://hdl.handle.net/21.11116/0000-000A-0C47-A

Genre: Conference Paper

Files

show Files

Locators

show

Creators

show

hide

Creators:
Goncharova, Anna¹, Author
Honigmann, Alf¹, Author
Jug, Florian¹, Author
Krull, Alexander¹, Author

Affiliations:
1Max Planck Institute for Molecular Cell Biology and Genetics, Max Planck Society, ou_2340692

Content

show

hide

Free keywords: -

Abstract: Many microscopy applications are limited by the total amount of usable light and are consequently challenged by the resulting levels of noise in the acquired images. This problem is often addressed via (supervised) deep learning based denoising. Recently, by making assumptions about the noise statistics, self-supervised methods have emerged. Such methods are trained directly on the images that are to be denoised and do not require additional paired training data. While achieving remarkable results, self-supervised methods can produce high-frequency artifacts and achieve inferior results compared to supervised approaches. Here we present a novel way to improve the quality of self-supervised denoising. Considering that light microscopy images are usually diffraction-limited, we propose to include this knowledge in the denoising process. We assume the clean image to be the result of a convolution with a point spread function (PSF) and explicitly include this operation at the end of our neural network. As a consequence, we are able to eliminate high-frequency artifacts and achieve self-supervised results that are very close to the ones achieved with traditional supervised methods.

Details

show

hide

Language(s):

Dates: Date issued: 2020-08-28

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.1007/978-3-030-66415-2_25
Other: cbg-8288

Degree: -

Event

show

hide

Title: 16th european conference on COMPUTER VISION 23-28 August 2020

Place of Event: online

Start-/End Date: 2020-08-23 - 2020-08-28

Legal Case

show

Project information

show

Source 1

show

hide

Title: Computer vision - ECCV 2020 workshops : Glasgow, UK, August 23-28, 2020 : proceedings : Part 1

Source Genre: Proceedings

Creator(s):
Bartoli, Adrien, Editor

Affiliations:
-

Publ. Info: Cham : Springer International Publishing

Pages: - Volume / Issue: Computer vision - ECCV 2020 workshops : Glasgow, UK, August 23-28, 2020 : proceedings : Part 1 Sequence Number: - Start / End Page: 380 - 393 Identifier: ISBN: 978-3-030-66414-5