Psgan: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening

• Published in: Proceedings - International Conference on Image Processing pp. 873 - 877
• Main Authors: Liu, Xiangyu, Wang, Yunhong, Liu, Qingjie
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2018
• Subjects: deep learning; Gallium nitride; GAN; Generators; Image fusion; pan-sharpening; Remote sensing; Spatial resolution; Task analysis; Training
• ISSN: 2381-8549
• DOI: 10.1109/ICIP.2018.8451049

Remote sensing image fusion (also known as pan-sharpening) aims to generate a high resolution multi -spectral image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral (MS) image. In this paper, we propose PSGAN, a generative adversarial network (GAN) for remote sensing image pansharpening. To the best of our knowledge, this is the first attempt at producing high quality pan-sharpened images with GANs. The PSGAN consists of two parts. Firstly, a two-stream fusion architecture is designed to generate the desired high resolution multi -spectral images, then a fully convolutional network serving as a discriminator is applied to distinct "real" or "pan-sharpened" MS images. Experiments on images acquired by Quickbird and GaoFen-1 satellites demonstrate that the proposed PSGAN can fuse PAN and MS images effectively and significantly improve the results over the state of the art traditional and CNN based pan-sharpening methods.