Noise reduction using diffusion models for SAR images
Encadrants : Florence Tupin, Emanuele Dalsasso
Email : florence.tupin@telecom-paris.fr
Disponible : OUI
Spécialité : IMA
Nombre d'étudiants : 1
Description : SAR (Synthetic Aperture Radar) images have the advantage of being
acquired at any time (day or night and whatever the weather conditions).
However, they are very noisy because of the speckle noise due to
coherent imaging. Recently, deep networks have provided impressive
speckle reduction results.
Travail demandé : The aim of this project is to experiment and evaluate a despeckling
strategy based on diffusion models.
Results produced in [1] will be reprocuded by training a network on SAR
images for speckle reduction. A comparison with other approaches like
[2] and [3] will be led.
Liens complémentaires : References
[1] SAR Despeckling using a Denoising Diffusion Probabilistic Model
Malsha V. Perera, Nithin Gopalakrishnan Nair, Wele Gedara Chaminda
Bandara, Vishal M. Patel
https://arxiv.org/abs/2206.04514
[2] SAR2SAR: a semi-supervised despeckling algorithm for SAR images
Emanuele Dalsasso, Loïc Denis, Florence Tupin
IEEE Journal of Selected Topics in Applied Earth Observations and Remote
Sensing, IEEE, In press, pp.1-1. ⟨10.1109/JSTARS.2021.3071864⟩
[3] As if by magic: self-supervised training of deep despeckling
networks with MERLIN
Emanuele Dalsasso, Loïc Denis, Florence Tupin
IEEE Transactions on Geoscience and Remote Sensing, Institute of
Electrical and Electronics Engineers, 2022
