Fast Portrait Matting Using Spatial Detail-Preserving Network

  • Shaofan Cai
  • Biao LengEmail author
  • Guanglu Song
  • Zheng Ge
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11306)


Image matting plays an important role in both computer vision and graphics applications. Natural image matting has recently made significant progress with the assistance of powerful Convolutional Neural Networks (CNN). However, it is often time-consuming for pixel-wise label inference. To get higher quality matting in an efficient way, we propose a well-designed SDPNet, which consists of two parallel branches—Semantic Segmentation Branch for half image resolution and Detail-Preserving Branch for full resolution, capturing both the semantic information and image details, respectively. Higher quality alpha matte can be generated while largely reducing the portion of computation. In addition, Spatial Attention Module and Boundary Refinement Module are proposed to extract distinguishable boundary features. Extensive Experiments show that SDPNet provides higher quality results on Portrait Matting benchmark, while obtaining 5x to 20x faster than previous methods.


Portrait Fast matting Detail-preserving Deep learning 



This work is supported by the National Natural Science Foundation of China (No. 61472023) and Beijing Municipal Natural Science Foundation (No. 4182034).


  1. 1.
    Aksoy, Y., Aydın, T.O., Pollefeys, M., Zürich, E.: Designing effective inter-pixel information flow for natural image matting. In: Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  2. 2.
    Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017)CrossRefGoogle Scholar
  3. 3.
    Barkau, R.L.: UNET: one-dimensional unsteady flow through a full network of open channels. Technical report, Hydrologic Engineering Center Davis CA (1996)Google Scholar
  4. 4.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. arXiv preprint arXiv:1606.00915 (2016)
  5. 5.
    Chen, Q., Li, D., Tang, C.K.: KNN matting. IEEE Trans. Pattern Anal. Mach. Intell. 35(9), 2175–2188 (2013)CrossRefGoogle Scholar
  6. 6.
    Cho, D., Tai, Y.-W., Kweon, I.: Natural image matting using deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 626–643. Springer, Cham (2016). Scholar
  7. 7.
    Chuang, Y.Y., Curless, B., Salesin, D.H., Szeliski, R.: A bayesian approach to digital matting. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 2, p. 2. IEEE (2001)Google Scholar
  8. 8.
    Gastal, E.S., Oliveira, M.M.: Shared sampling for real-time alpha matting. In: Computer Graphics Forum, vol. 29, pp. 575–584. Wiley Online Library (2010)Google Scholar
  9. 9.
    He, K., Sun, J., Tang, X.: Fast matting using large kernel matting laplacian matrices. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2165–2172. IEEE (2010)Google Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)Google Scholar
  11. 11.
    Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 228–242 (2008)CrossRefGoogle Scholar
  12. 12.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)Google Scholar
  13. 13.
    Rhemann, C., Rother, C., Wang, J., Gelautz, M., Kohli, P., Rott, P.: A perceptually motivated online benchmark for image matting. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 1826–1833. IEEE (2009)Google Scholar
  14. 14.
    Shen, X., Tao, X., Gao, H., Zhou, C., Jia, J.: Deep automatic portrait matting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 92–107. Springer, Cham (2016). Scholar
  15. 15.
    Wang, F., et al.: Residual attention network for image classification. arXiv preprint arXiv:1704.06904 (2017)
  16. 16.
    Wang, J., Agrawala, M., Cohen, M.F.: Soft scissors: an interactive tool for realtime high quality matting. ACM Trans. Graph. (TOG) 26(3), 9 (2007)CrossRefGoogle Scholar
  17. 17.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987–5995. IEEE (2017)Google Scholar
  18. 18.
    Xu, N., Price, B., Cohen, S., Huang, T.: Deep image matting. In: Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  19. 19.
    Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. arXiv preprint arXiv:1704.08545 (2017)
  20. 20.
    Zhu, B., Chen, Y., Wang, J., Liu, S., Zhang, B., Tang, M.: Fast deep matting for portrait animation on mobile phone. In: Proceedings of the 2017 ACM on Multimedia Conference, pp. 297–305. ACM (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Shaofan Cai
    • 1
  • Biao Leng
    • 1
    Email author
  • Guanglu Song
    • 1
  • Zheng Ge
    • 2
  1. 1.School of Computer Science and EngineeringBeihang UniversityBeijingChina
  2. 2.Graduate School of Information, Production and SystemsWaseda UniversityKitakyushuJapan

Personalised recommendations