Transformer-based SAR Image Despeckling

2022/01/23 by Perera, Malsha V., Bandara, Wele Gedara Chaminda, Valanarasu, Jeya Maria Jose +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2201.09355

Abstract

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.

Cited by

• γ-Bridge: A Look-Parametric Diffusion Bridge
• Towards Frequency-Adaptive Learning for SAR Despeckling

Related

• SAR image despeckling through convolutional neural networks
• SAR Despeckling Using Overcomplete Convolutional Networks
• Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks
• Learning a Dilated Residual Network for SAR Image Despeckling
• Towards Frequency-Adaptive Learning for SAR Despeckling