Communication Dans Un Congrès Année : 2024

On the impact of despeckling for supervised SAR super-resolution

Résumé

Enhancement of SAR resolution is essential for various applications in earth observation. Since SAR images are highly corrupted by speckle noise, we propose to help super-resolution neural network learning with a despeckling preprocessing step. Unlike optical images, low-resolution SAR images are extracted from the sub-apertures of the original SAR image. To evaluate the impact of the despeckling, SwinIR, SRCNN, and ESPCN neural networks are trained in three ways: Noisy2Noisy, Noisy2Denoised, and Denoised2Denoised. The ONERA SAR database experiments show the despeckling improvement gap and the slight enhancement of SwinIR over SRCNN and ESPCN according to the visual reconstruction and to L 1 , L 2 , PSNR, and SSIM metrics
Fichier principal
Vignette du fichier
Papier_Superresolution.pdf (3.72 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04914978 , version 1 (27-01-2025)

Licence

Identifiants

  • HAL Id : hal-04914978 , version 1

Citer

Max Muzeau, Chengfang Ren, Jérémy Fix, Frederic Brigui, Jean-Philippe Ovarlez. On the impact of despeckling for supervised SAR super-resolution. EUSAR 2024, Apr 2024, Munich, Germany. ⟨hal-04914978⟩
0 Consultations
0 Téléchargements

Partager

More