SFTGAN: a generative adversarial network for pan-sharpening equipped with spatial feature transform layers

Yutian Zhang; Xiaohua Li; Jiliu Zhou

doi:10.1117/1.JRS.13.026507

22 May 2019 SFTGAN: a generative adversarial network for pan-sharpening equipped with spatial feature transform layers

Yutian Zhang, Xiaohua Li, Jiliu Zhou

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 13, Issue 2, 026507 (May 2019). https://doi.org/10.1117/1.JRS.13.026507

Abstract

Pan-sharpening is an indispensable technology for remote sensing that aims to combine low-resolution multispectral images and high-resolution panchromatic images to create a multispectral image with high resolution. However, pan-sharpening approaches often encounter spectral distortion and detail distortion issues. In order to overcome the drawbacks of pan-sharpening methodologies, we propose an end-to-end pan-sharpening model consisting of an effective generative adversarial network architecture equipped with spatial feature transform layers that generate spatial detail features under spectral feature constraints. Through a large number of quantitative and visual assessments, we demonstrate that the proposed method achieves superior performance to other state-of-the-art methods.

Citation Download Citation

Yutian Zhang, Xiaohua Li, and Jiliu Zhou "SFTGAN: a generative adversarial network for pan-sharpening equipped with spatial feature transform layers," Journal of Applied Remote Sensing 13(2), 026507 (22 May 2019). https://doi.org/10.1117/1.JRS.13.026507

Received: 27 November 2018; Accepted: 29 April 2019; Published: 22 May 2019

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available