Abstract | ||
---|---|---|
Deblurring is a classical problem for remote sensing images, which is known to be difficult as an ill-posed problem. A feasible solution for the problem is incorporating various priors into restoration procedure as constrained conditions. However, the learning of priors usually assumes that the blurs in an image are produced by fixed types of reasons, and thus a possible decrease in model's description ability. In this paper, an end-to-end learned method based on generative adversarial networks (GANs) is proposed to tackle the deblurring problem for remote sensing images. The proposed deblurring model does not need any prior assumptions for the blurs. The proposed method was evaluated on a satellite map image data set and state-of-the-art performance was obtained. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/GEOINFORMATICS.2018.8557110 | 2018 26TH INTERNATIONAL CONFERENCE ON GEOINFORMATICS (GEOINFORMATICS 2018) |
Keywords | Field | DocType |
Generative Adversatial Network (GAN), image deblurring, remote sensing image, loss function | Generative adversarial network,Deblurring,Computer science,Remote sensing,Generative grammar,Prior probability,Adversarial system | Conference |
ISSN | Citations | PageRank |
2161-024X | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yungang Zhang | 1 | 87 | 10.05 |
Yu Xiang | 2 | 82 | 18.60 |
Lei Bai | 3 | 0 | 0.34 |