Remote Sensing Image Deblurring Algorithm Based on WGAN

  • Haiying XiaEmail author
  • Chenxu Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11434)


Remote sensing images are blurred due to large and wide imaging, long shooting distance, fast scanning speed, interference from external light, etc. At the same time, because of that remote sensing images have the characteristics of diverse and dense shooting objects, deblurring remote sensing images is a major problem in remote sensing research. Therefore, we propose a remote sensing image deblurring algorithm, which based on WGAN. The algorithm is different from the traditional method in estimating the blur kernel of image. What’s more our method does not require an explicit estimation of the blur kernel, and it implements an end-to-end image deblurring process. We use a WGAN-based deblurring model. First, the training images are processed in pairs. Then, in order to increase the generalization ability, a image of 256 * 256 that is a sub-region cropped at the random position in the original image is chosen as the input image. Finally, to achieve a better deblurring effect, a content loss function and a perceptual loss function are added to the loss function to achieve the specific implementation. The remote sensing image deblurring model trained by the proposed method has achieved better results on the remote sensing image dataset. The experimental results show that the proposed algorithm have better performance than the traditional method in filtering out the blur of remote sensing images, which could optimize the overall visual effect subjectively and improve the peak signal-to-noise ratio of the image objectively.


Remote sensing image Motion blur Deblurring Generative Adversarial Networks Deep learning 



This work is supported by the National Natural Science Foundation of China (No. 61762014). The project was funded by a major project of Guangxi Science and Technology (Guike AA18118009).


  1. 1.
    Tan, H.P., et al.: Multi-scale deblurring of remote sensing images based on regularization constraints. J. Image Graph. 20(3), 386–394 (2015)Google Scholar
  2. 2.
    Cheng, F.: Deblurring of optical remote sensing image based on estimated point spread function. Shanghai Aerosp. 33(3), 105–112 (2016)Google Scholar
  3. 3.
    Zhang, G.M., et al.: Remote image restoration method based on blurry image and noise image. Electron. Des. Eng. 25(18), 82–86 (2017)Google Scholar
  4. 4.
    Ren, J.J., et al.: Image deblurring based on fast convolutional neural networks. J. Comput. Aided Des. Comput. Graph. 29(8), 1444–1456 (2017)Google Scholar
  5. 5.
    Nah, S., Kim, T.H., et al.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: IEEE Conference on Computer Vision and Pattern Recognition 2017, pp. 257–265 (2017)Google Scholar
  6. 6.
    Kupyn, O., Budzan, V., et al.: DeblurGAN: blind motion deblurring using conditional adversarial networks. arXiv preprint arXiv:1711.07064, pp. 1–7 (2018)
  7. 7.
    Goodfellow, I.J., Pouget-Abadie, J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing System, pp. 2672–2680 (2014)Google Scholar
  8. 8.
    Arjovsky, M., Chintala, S., et al: Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017)
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). Scholar
  10. 10.
    Gulrajani, I., Ahmed, F., et al.: Improved Training of Wasserstein GANs. arXiv preprint arXiv:1704.00028 (2017)
  11. 11.
    Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). Scholar
  12. 12.
    Simonyan, K., Zisserman, A., et al.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations, abs/1409.1555 (2014)Google Scholar
  13. 13.
    Xu, B., Wang, N. et al: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.College of Electronic EngineeringGuangxi Normal UniversityGuilinChina

Personalised recommendations