Next Article in Journal
Domain Adaptive Ship Detection in Optical Remote Sensing Images
Next Article in Special Issue
Guaranteed Robust Tensor Completion via ∗L-SVD with Applications to Remote Sensing Data
Previous Article in Journal
Estimating the Fractional Cycle Biases for GPS Triple-Frequency Precise Point Positioning with Ambiguity Resolution Based on IGS Ultra-Rapid Predicted Orbits
Previous Article in Special Issue
Mid-Infrared Compressive Hyperspectral Imaging
Article

Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks

1
School of Electronic Engineering, Xidian Universerty, Xi’an 710071, China
2
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China
*
Author to whom correspondence should be addressed.
Academic Editors: Karen Egiazarian, Vladimir Lukin and Aleksandra Pizurica
Remote Sens. 2021, 13(16), 3167; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163167
Received: 15 June 2021 / Revised: 25 July 2021 / Accepted: 6 August 2021 / Published: 10 August 2021
(This article belongs to the Special Issue Remote Sensing Image Denoising, Restoration and Reconstruction)
Mainstream image super-resolution (SR) methods are generally based on paired training samples. As the high-resolution (HR) remote sensing images are difficult to collect with a limited imaging device, most of the existing remote sensing super-resolution methods try to down-sample the collected original images to generate an auxiliary low-resolution (LR) image and form a paired pseudo HR-LR dataset for training. However, the distribution of the generated LR images is generally inconsistent with the real images due to the limitation of remote sensing imaging devices. In this paper, we propose a perceptually unpaired super-resolution method by constructing a multi-stage aggregation network (MSAN). The optimization of the network depends on consistency losses. In particular, the first phase is to preserve the contents of the super-resolved results, by constraining the content consistency between the down-scaled SR results and the low-quality low-resolution inputs. The second stage minimizes perceptual feature loss between the current result and LR input to constrain perceptual-content consistency. The final phase employs the generative adversarial network (GAN) to adding photo-realistic textures by constraining perceptual-distribution consistency. Numerous experiments on synthetic remote sensing datasets and real remote sensing images show that our method obtains more plausible results than other SR methods quantitatively and qualitatively. The PSNR of our network is 0.06dB higher than the SOTA method—HAN on the UC Merced test set with complex degradation. View Full-Text
Keywords: remote sensing; unpaired super-resolution; multi-stage aggregation network; consistency losses remote sensing; unpaired super-resolution; multi-stage aggregation network; consistency losses
Show Figures

Figure 1

MDPI and ACS Style

Zhang, L.; Lu, W.; Huang, Y.; Sun, X.; Zhang, H. Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks. Remote Sens. 2021, 13, 3167. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163167

AMA Style

Zhang L, Lu W, Huang Y, Sun X, Zhang H. Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks. Remote Sensing. 2021; 13(16):3167. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163167

Chicago/Turabian Style

Zhang, Lize, Wen Lu, Yuanfei Huang, Xiaopeng Sun, and Hongyi Zhang. 2021. "Unpaired Remote Sensing Image Super-Resolution with Multi-Stage Aggregation Networks" Remote Sensing 13, no. 16: 3167. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13163167

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop