Transformer-based SAR Image Despeckling

• Main Authors: Perera, Malsha V, Bandara, Wele Gedara Chaminda, Valanarasu, Jeya Maria Jose, Patel, Vishal M
• Format: Journal Article
• Language: English
• Published: 23-01-2022
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2201.09355

Synthetic Aperture Radar (SAR) images are usually degraded by a
multiplicative noise known as speckle which makes processing and interpretation
of SAR images difficult. In this paper, we introduce a transformer-based
network for SAR image despeckling. The proposed despeckling network comprises
of a transformer-based encoder which allows the network to learn global
dependencies between different image regions - aiding in better despeckling.
The network is trained end-to-end with synthetically generated speckled images
using a composite loss function. Experiments show that the proposed method
achieves significant improvements over traditional and convolutional neural
network-based despeckling methods on both synthetic and real SAR images.