Advertisement

Improving Large Pose Face Alignment by Regressing 2D and 3D Landmarks Simultaneously and Visibility Refinement

  • Xu Luo
  • Pengfei Li
  • Fuxuan Chen
  • Qijun Zhao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

This paper proposes an improved method for large pose face alignment. Unlike existing methods, the proposed method regresses both 2D and 3D coordinates of facial landmarks simultaneously. It first computes a coarse estimation of the landmarks via a shape regression network (SRN) whose input is only the input image. It then refines the landmarks with another SRN whose input consists of three components: the transformed image, the visible landmark heatmap and the feature map from the first SRN. These components are constructed by a transformation module based on the current estimates of 3D and 2D landmarks. By effectively exploring the 3D property of faces for constraining 2D landmarks and refining their visibility, the proposed method can better align faces under large poses. Extensive experiments on three public databases demonstrate the superiority of the proposed method in large pose face alignment.

Keywords

Face alignment 3D/2D facial landmarks Cascaded shape regression Visible landmark heatmap 

Notes

Acknowledgements

This work is supported by the National Key Research and Development Program of China (2017YFB0802300) and the National Natural Science Foundation of China (61773270).

References

  1. 1.
    Zhou, S., Comaniciu, D.: Shape regression machine. Inf. Process. Med. Imaging 45(84), 13–25 (2007)Google Scholar
  2. 2.
    Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: CVPR, pp. 3476–3483 (2013)Google Scholar
  3. 3.
    Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial Landmark Detection by Deep Multi-task Learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94–108. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10599-4_7CrossRefGoogle Scholar
  4. 4.
    Zhu, S., Li, C., Chen, CL., Tang, X.: Face alignment by coarse-to-fine shape searching. In: CVPR, pp. 4998–5006 (2015)Google Scholar
  5. 5.
    Kowalski, M., Naruniec, J., Trzcinski, T.: Deep alignment network: a convolutional neural network for robust face alignment. In: CVPRW, pp. 2034–2043 (2017)Google Scholar
  6. 6.
    Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2D&3D face alignment problem? (and a dataset of 230,000 3D facial landmarks). In: ICCV, pp. 1021–1030 (2017)Google Scholar
  7. 7.
    Jourabloo, A., Liu, X.: Pose-invariant 3D face alignment. In: ICCV, pp. 3694–3702 (2015)Google Scholar
  8. 8.
    Liu, F., Zeng, D., Zhao, Q., Liu, X.: Joint Face Alignment and 3D Face Reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 545–560. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_33CrossRefGoogle Scholar
  9. 9.
    Zhu, X., Lei, Z., Liu, X., Shi, H., Li, S.: Face alignment across large poses: a 3D solution. In: CVPR, pp. 146–155 (2016)Google Scholar
  10. 10.
    Chen, F., Liu, F., Zhao, Q.: Robust Multi-view Face Alignment Based on Cascaded 2D/3D Face Shape Regression. In: You, Z., Zhou, J., Wang, Y., Sun, Z., Shan, S., Zheng, W., Feng, J., Zhao, Q. (eds.) CCBR 2016. LNCS, vol. 9967, pp. 40–49. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46654-5_5CrossRefGoogle Scholar
  11. 11.
    Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE Trans. Pattern Anal. Mach. Intell. 25(9), 1063–1074 (2003)CrossRefGoogle Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint, pp. 1409–1556 (2014)Google Scholar
  13. 13.
    Tuzel, O., Marks, T.K., Tambe, S.: Robust Face Alignment Using a Mixture of Invariant Experts. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 825–841. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46454-1_50CrossRefGoogle Scholar
  14. 14.
    Kingma, D., Adam, J.: A method for stochastic optimization. In: International Conference on Learning Representations, pp. 1–13 (2014)Google Scholar
  15. 15.
    Zafeiriou, S., Trigeorgis, G., Chrysos, G., Deng, J., Shen, J.: The menpo facial landmark localisation challenge: a step closer to the solution. In: CVPRW, pp. 2116–2125 (2017)Google Scholar
  16. 16.
    Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: ICCVW, pp. 397–403 (2013)Google Scholar
  17. 17.
    Burgos-Artizzu, X., Perona, P., Dollar, P.: Robust face landmark estimation under occlusion. In: ICCV, pp. 1513–1520 (2013)Google Scholar
  18. 18.
    Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. Int. J. Comput. Vis. 107(2), 177–190 (2014)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Xiong, X., Torre, F.: Supervised descent method and its applications to face alignment. In: CVPR, pp. 532–539 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.National Key Laboratory of Fundamental Science on Synthetic Vision, College of Computer ScienceSichuan UniversityChengduChina

Personalised recommendations