期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 12, 页码 10227-10242出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3042974
关键词
Generative adversarial networks; Generators; Neural networks; Computer architecture; Training; Spatial resolution; Data models; Convolutional neural network (CNN); deep learning; generative adversarial network (GAN); pan-sharpening; residual learning
类别
资金
- NSFC [41871283, 61601011]
The article introduces a novel method PSGAN based on generative adversarial learning, which can generate high-quality pan-sharpened images and has achieved good performance.
This article addresses the problem of remote sensing image pan-sharpening from the perspective of generative adversarial learning. We propose a novel deep neural network-based method named pansharpening GAN (PSGAN). To the best of our knowledge, this is one of the first attempts at producing high-quality pan-sharpened images with generative adversarial networks (GANs). The PSGAN consists of two components: a generative network (i.e., generator) and a discriminative network (i.e., discriminator). The generator is designed to accept panchromatic (PAN) and multispectral (MS) images as inputs and maps them to the desired high-resolution (HR) MS images, and the discriminator implements the adversarial training strategy for generating higher fidelity pan-sharpened images. In this article, we evaluate several architectures and designs, namely, two-stream input, stacking input, batch normalization layer, and attention mechanism to find the optimal solution for pan-sharpening. Extensive experiments on QuickBird, GaoFen-2, and WorldView-2 satellite images demonstrate that the proposed PSGANs not only are effective in generating high-quality HR MS images and superior to state-of-the-art methods but also generalize well to full-scale images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据