Range Scaling Global U-Net for Perceptual Image Enhancement on Mobile Devices

  • Jie Huang
  • Pengfei ZhuEmail author
  • Mingrui Geng
  • Jiewen Ran
  • Xingguang Zhou
  • Chen Xing
  • Pengfei Wan
  • Xiangyang Ji
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11133)


Perceptual image enhancement on mobile devices—smart phones in particular—has drawn increasing industrial efforts and academic interests recently. Compared to digital single-lens reflex (DSLR) cameras, cameras on smart phones typically capture lower-quality images due to various hardware constraints. Without additional information, it is a challenging task to enhance the perceptual quality of a single image especially when the computation has to be done on mobile devices. In this paper we present a novel deep learning based approach—the Range Scaling Global U-Net (RSGUNet)—for perceptual image enhancement on mobile devices. Besides the U-Net structure that exploits image features at different resolutions, proposed RSGUNet learns a global feature vector as well as a novel range scaling layer that alleviate artifacts in the enhanced images. Extensive experiments show that the RSGUNet not only outputs enhanced images with higher subjective and objective quality, but also takes less inference time. Our proposal wins the 1st place by a great margin in track B of the Perceptual Image Enhancement on Smartphones Challenge (PRIM2018). Code is available at


Perceptual image enhancement Global feature vector Range scaling layer 

Supplementary material (38.3 mb)
Supplementary material 1 (zip 39194 KB)


  1. 1.
    Ignatov, A., Kobyshev, N., Timofte, R., Vanhoey, K., Van Gool, L.: DSLR-quality photos on mobile devices with deep convolutional networks. In: The IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  2. 2.
    Chen, Y.S., Wang, Y.C., Kao, M.H., Chuang, Y.Y.: Deep photo enhancer: unpaired learning for image enhancement from photographs with GANS. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6306–6314 (2018)Google Scholar
  3. 3.
    Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)Google Scholar
  4. 4.
    Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., Yang, M.-H.: Single image dehazing via multi-scale convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 154–169. Springer, Cham (2016). Scholar
  5. 5.
    Ignatov, A., Timofte, R., et al.: PIRM challenge on perceptual image enhancement on smartphones: report. In: European Conference on Computer Vision Workshops (2018)Google Scholar
  6. 6.
    Divya, K., Roshna, K.: A survey on various image enhancement algorithms for naturalness preservation. Int. J. Comput. Sci. Inf. Technol. 6(3), 2043–2045 (2015)Google Scholar
  7. 7.
    Bedi, S., Khandelwal, R.: Various image enhancement techniques-a critical review. Int. J. Adv. Res. Comput. Commun. Eng. 2(3), 267–274 (2013)Google Scholar
  8. 8.
    Yang, F., Wu, J.: An improved image contrast enhancement in multiple-peak images based on histogram equalization. In: 2010 International Conference on Computer Design and Applications (ICCDA), vol. 1, pp. V1–346. IEEE (2010)Google Scholar
  9. 9.
    Rajavel, P.: Image dependent brightness preserving histogram equalization. IEEE Trans. Consum. Electron. 56(2), 756–763 (2010)CrossRefGoogle Scholar
  10. 10.
    Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). Scholar
  11. 11.
    Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646–1654 (2016)Google Scholar
  12. 12.
    Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2017)Google Scholar
  13. 13.
    Kligvasser, I., Shaham, T.R., Michaeli, T.: xunit: learning a spatial activation function for efficient image restoration. In: CVPR (2018)Google Scholar
  14. 14.
    Noroozi, M., Chandramouli, P., Favaro, P.: Motion deblurring in the wild. In: Roth, V., Vetter, T. (eds.) GCPR 2017. LNCS, vol. 10496, pp. 65–77. Springer, Cham (2017). Scholar
  15. 15.
    Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep cnn for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Yan, Z., Zhang, H., Wang, B., Paris, S., Yu, Y.: Automatic photo adjustment using deep neural networks. ACM Trans. Graph. (TOG) 35(2), 11 (2016)CrossRefGoogle Scholar
  17. 17.
    Sajjadi, M.S., Schölkopf, B., Hirsch, M.: Enhancenet: single image super-resolution through automated texture synthesis. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 4501–4510. IEEE (2017)Google Scholar
  18. 18.
    Gharbi, M., Chen, J., Barron, J.T., Hasinoff, S.W., Durand, F.: Deep bilateral learning for real-time image enhancement. ACM Trans. Graph. (TOG) 36(4), 118 (2017)CrossRefGoogle Scholar
  19. 19.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  20. 20.
    Chen, J., Adams, A., Wadhwa, N., Hasinoff, S.W.: Bilateral guided upsampling. ACM Trans. Graph. (TOG) 35(6), 203 (2016)CrossRefGoogle Scholar
  21. 21.
    Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47–57 (2017)CrossRefGoogle Scholar
  22. 22.
    Ustyuzhaninov, I., Brendel, W., Gatys, L., Bethge, M.: What does it take to generate natural textures? In: International Conference on Learning Representations (2017)Google Scholar
  23. 23.
    Aly, H.A., Dubois, E.: Image up-sampling using total-variation regularization with a new observation model. IEEE Trans. Image Process. 14(10), 1647–1659 (2005)CrossRefGoogle Scholar
  24. 24.
    Blau, Y., Michaeli, T.: The perception-distortion tradeoff. In: CVPR (2018)Google Scholar
  25. 25.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jie Huang
    • 1
  • Pengfei Zhu
    • 1
    Email author
  • Mingrui Geng
    • 1
  • Jiewen Ran
    • 1
  • Xingguang Zhou
    • 1
  • Chen Xing
    • 1
  • Pengfei Wan
    • 2
  • Xiangyang Ji
    • 2
  1. 1.MTlabMeitu Inc.XiamenChina
  2. 2.Tsinghua UniversityBeijingChina

Personalised recommendations