论文标题
通过盲点卷积神经网络进行深度无监督的SAR伪装
Towards Deep Unsupervised SAR Despeckling with Blind-Spot Convolutional Neural Networks
论文作者
论文摘要
SAR Despeckling在遥感中是至关重要的问题，因为它代表了许多场景分析算法的第一步。最近，深度学习技术胜过基于古典模型的选算算法。但是，这样的方法需要清洁的地面真相图像进行训练，因此诉诸于合成斑点的光学图像，因为无法获取干净的SAR图像。在本文中，受到盲点DeNoising网络的最新作品的启发，我们提出了一种自欺欺人的贝叶斯式佩克林方法。所提出的方法是仅采用嘈杂图像的训练，因此可以学习真实SAR图像的特征而不是合成数据。我们表明，所提出的网络的性能非常接近于综合数据的监督培训方法和对真实数据的竞争。
SAR despeckling is a problem of paramount importance in remote sensing, since it represents the first step of many scene analysis algorithms. Recently, deep learning techniques have outperformed classical model-based despeckling algorithms. However, such methods require clean ground truth images for training, thus resorting to synthetically speckled optical images since clean SAR images cannot be acquired. In this paper, inspired by recent works on blind-spot denoising networks, we propose a self-supervised Bayesian despeckling method. The proposed method is trained employing only noisy images and can therefore learn features of real SAR images rather than synthetic data. We show that the performance of the proposed network is very close to the supervised training approach on synthetic data and competitive on real data.
