As if by magic: self-supervised training of deep despeckling networks with MERLIN

Emanuele Dalsasso (1, 2, 3, 4) , Loïc Denis (5) , Florence Tupin (1, 2, 3, 4)

1 IMAGES - Image, Modélisation, Analyse, GEométrie, Synthèse
2 IDS - Département Images, Données, Signal
3 IP Paris - Institut Polytechnique de Paris
4 LTCI - Laboratoire Traitement et Communication de l'Information
5 LHC - Laboratoire Hubert Curien [Saint Etienne]

Domains: Engineering Sciences [physics]; Signal and Image processing

Emanuele Dalsasso, Loïc Denis, Florence Tupin. As if by magic: self-supervised training of deep despeckling networks with MERLIN. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60. ⟨ujm-03270455v2⟩