Skip to Main content Skip to Navigation

Remote Sensing Single-Image Resolution Improvement Using A Deep Gradient-Aware Network with Image-Specific Enhancement

Abstract : Super-resolution (SR) is able to improve the spatial resolution of remote sensing images, which is critical for many practical applications such as fine urban monitoring. In this paper, a new single-image SR method, deep gradient-aware network with image-specific enhancement (DGANet-ISE) was proposed to improve the spatial resolution of remote sensing images. First, DGANet was proposed to model the complex relationship between low-and high-resolution images. A new gradient-aware loss was designed in the training phase to preserve more gradient details in super-resolved remote sensing images. Then, the ISE approach was proposed in the testing phase to further improve the SR performance. By using the specific features of each test image, ISE can further boost the generalization capability and adaptability of our method on inexperienced datasets. Finally, three datasets were used to verify the effectiveness of our method. The results indicate that DGANet-ISE outperforms the other 14 methods in the remote sensing image SR, and the cross-database test results demonstrate that our method exhibits satisfactory generalization performance in adapting to new data.
Complete list of metadatas

Cited literature [57 references]  Display  Hide  Download

https://hal-amu.archives-ouvertes.fr/hal-02492404
Contributor : Sébastien Mavromatis <>
Submitted on : Wednesday, February 26, 2020 - 9:50:29 PM
Last modification on : Friday, February 28, 2020 - 1:31:26 AM

File

remotesensing-12-00758.pdf
Publisher files allowed on an open archive

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

Mengjiao Qin, Sébastien Mavromatis, Linshu Hu, Feng Zhang, Renyi Liu, et al.. Remote Sensing Single-Image Resolution Improvement Using A Deep Gradient-Aware Network with Image-Specific Enhancement. Remote Sensing, MDPI, 2020, ⟨10.3390/rs12050758⟩. ⟨hal-02492404⟩

Share

Metrics

Record views

55

Files downloads

87