Skip to Main content Skip to Navigation
Conference papers

A ''learn 2D, apply 3D'' method for 3D deconvolution microscopy

Ferréol Soulez 1
1 AiRi
CRAL - Centre de Recherche Astrophysique de Lyon
Abstract : This paper presents a 3D deconvolution method for fluorescence microscopy that reached the first place at the ''the 3D Deconvolution Microscopy Challenge'' held during ISBI 2013. It uses sparse coding algorithm to learn 2D ''high resolution'' features that will be used as a prior to enhance the resolution along depth axis. This is a three steps method: (i) deconvolution step with total variation regularization, (ii) denoising of the deconvolved image using learned sparse coding, (iii) deconvolution using denoised image as quadratic prior. Its effectiveness is illustrated on both synthetic and real data.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download
Contributor : Ferréol Soulez <>
Submitted on : Friday, December 6, 2013 - 11:00:48 AM
Last modification on : Wednesday, November 20, 2019 - 2:56:54 AM
Document(s) archivé(s) le : Saturday, April 8, 2017 - 5:03:00 AM


Files produced by the author(s)


  • HAL Id : hal-00914839, version 1



Ferréol Soulez. A ''learn 2D, apply 3D'' method for 3D deconvolution microscopy. International symposium on biomedical imaging, May 2014, Beijing, China. ⟨hal-00914839⟩



Record views


Files downloads