Self-supervised training strategies for SAR image despeckling with deep neural networks - Archive ouverte HAL Access content directly
Conference Papers Year :

Self-supervised training strategies for SAR image despeckling with deep neural networks

(1, 2, 3) , (4) , (5, 6) , (1, 2, 3)
1
2
3
4
5
6

Abstract

Images acquired by Synthetic Aperture Radar (SAR) are affected by speckle, making their interpretation difficult. Most recently, the rise of deep learning algorithms has led to groundbreaking results. The training of a neural network typically requires matched pairs of speckled / speckle-free images. To account for the speckle present in actual images and simplify the generation of training sets, self-supervision approaches directly train the network on speckled SAR data. Self-supervision exploits a form of diversity, either temporal, spatial, or based on the real/imaginary parts. We compare the requirements in terms of data preprocessing and the performance of three self-supervised strategies.
Fichier principal
Vignette du fichier
EUSAR2022.pdf (6.89 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03589245 , version 1 (25-02-2022)
hal-03589245 , version 2 (03-08-2022)

Identifiers

  • HAL Id : hal-03589245 , version 2

Cite

Emanuele Dalsasso, Loïc Denis, Max Muzeau, Florence Tupin. Self-supervised training strategies for SAR image despeckling with deep neural networks. 14th European Conference on Synthetic Aperture Radar (EUSAR), Jul 2022, Leipzig, Germany. ⟨hal-03589245v2⟩
368 View
173 Download

Share

Gmail Facebook Twitter LinkedIn More