Noise reduction using diffusion models for SAR images
Encadrants : Florence Tupin, Emanuele Dalsasso
Email : firstname.lastname@example.org
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  will be reprocuded by training a network on SAR images for speckle reduction. A comparison with other approaches like  and  will be led.
Liens complémentaires : References  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  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⟩  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