Face Super-Resolution Guided by 3D Facial Priors

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12349)


State-of-the-art face super-resolution methods employ deep convolutional neural networks to learn a mapping between low- and high-resolution facial patterns by exploring local appearance knowledge. However, most of these methods do not well exploit facial structures and identity information, and struggle to deal with facial images that exhibit large pose variations. In this paper, we propose a novel face super-resolution method that explicitly incorporates 3D facial priors which grasp the sharp facial structures. Our work is the first to explore 3D morphable knowledge based on the fusion of parametric descriptions of face attributes (e.g., identity, facial expression, texture, illumination, and face pose). Furthermore, the priors can easily be incorporated into any network and are extremely efficient in improving the performance and accelerating the convergence speed. Firstly, a 3D face rendering branch is set up to obtain 3D priors of salient facial structures and identity knowledge. Secondly, the Spatial Attention Module is used to better exploit this hierarchical information (i.e., intensity similarity, 3D facial structure, and identity content) for the super-resolution problem. Extensive experiments demonstrate that the proposed 3D priors achieve superior face super-resolution results over the state-of-the-arts.


Face super-resolution 3D facial priors Facial structures and identity knowledge 



This work is supported by the National Key R&D Program of China under Grant 2018AAA0102503, Zhejiang Lab (NO.2019NB0AB01), Beijing Education Committee Cooperation Beijing Natural Science Foundation (No. KZ201910005007), National Natural Science Foundation of China (No. U1736219) and Peng Cheng Laboratory Project of Guangdong Province PCL2018KP004.

Supplementary material

504439_1_En_44_MOESM1_ESM.pdf (9.9 mb)
Supplementary material 1 (pdf 10172 KB)


  1. 1.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In ACM SIGGRAPH (1999)Google Scholar
  2. 2.
    Booth, J., Roussos, A., Zafeiriou, S., Ponniah, A., Dunaway, D.: A 3D morphable model learnt from 10,000 faces. In: CVPR (2016)Google Scholar
  3. 3.
    Cao, Q., Lin, L., Shi, Y., Liang, X., Li, G.: Attention-aware face hallucination via deep reinforcement learning. In: CVPR (2017)Google Scholar
  4. 4.
    Chen, Y., Tai, Y., Liu, X., Shen, C., Yang, J.: FSRNet: end-to-end learning face super-resolution with facial priors. In: CVPR (2018)Google Scholar
  5. 5.
    Dahl, R., Norouzi, M., Shlens, J.: Pixel recursive super resolution. In: ICCV (2017)Google Scholar
  6. 6.
    Deng, Y., Yang, J., Xu, S., Chen, D., Jia, Y., Tong, X.: Accurate 3D face reconstruction with weakly-supervised learning: from single image to image set. In: CVPRW (2019)Google Scholar
  7. 7.
    Dong, C., Loy, C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. TPAMI 38(2), 295–307 (2016)CrossRefGoogle Scholar
  8. 8.
    Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016). Scholar
  9. 9.
    Fritsche, M., Gu, S., Timofte, R.: Frequency separation for real-world super-resolution. In: CVPRW (2019)Google Scholar
  10. 10.
    Grm, K., Scheirer, W., Štruc, V.: Face hallucination using cascaded super-resolution and identity priors. TIP 29, 2150–2165 (2019)Google Scholar
  11. 11.
    Han, C., Shan, S., Kan, M., Wu, S., Chen, X.: Face recognition with contrastive convolution. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 120–135. Springer, Cham (2018). Scholar
  12. 12.
    Haris, M., Shakhnarovich, G., Ukita, N.: Deep back projection networks for super-resolution. In: CVPR (2018)Google Scholar
  13. 13.
    Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)Google Scholar
  14. 14.
    Huang, H., He, R., Sun, Z., Tan, T.: Wavelet-SRNet: a wavelet-based CNN for multi-scale face super resolution. In: ICCV (2017)Google Scholar
  15. 15.
    Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. In: NIPS (2015)Google Scholar
  16. 16.
    Kim, D., Kim, M., Kwon, G., Kim, D.: Progressive face super-resolution via attention to facial landmark. In: BMVC (2019)Google Scholar
  17. 17.
    Kim, J., Lee, J., Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: CVPR (2016)Google Scholar
  18. 18.
    Kim, J., Lee, J., Lee, K.: Deeply recursive convolutional network for image super-resolution. In: CVPR (2016)Google Scholar
  19. 19.
    Lai, W., Huang, J., Ahuja, N., Yang, M.: Deep Laplacian pyramid networks for fast and accurate super-resolution. In: CVPR (2017)Google Scholar
  20. 20.
    Li, Z., Tang, J., Zhang, L., Yang, J.: Weakly-supervised semantic guided hashing for social image retrieval. Int. J. Comput. Vision 128(8), 2265–2278 (2020). Scholar
  21. 21.
    Lian, S., Zhou, H., Sun, Y.: A feature-guided super-resolution generative adversarial network for unpaired image super-resolution. In: NIPS (2019)Google Scholar
  22. 22.
    Lim, B., Son, S., Kim, H., Nah, S., Lee, K.: Enhanced deep residual networks for single image super-resolution. In: CVPRW, pp. 1646–1654 (2017)Google Scholar
  23. 23.
    Liu, C., Shum, H., Freeman, W.: Face hallucination: theory and practice. Int. J. Comput. Vision 75(1), 115–134 (2007). Scholar
  24. 24.
    Liu, W., Lin, D., Tang, X.: Hallucinating faces: TensorPatch super-resolution and coupled residue compensation. In: CVPR (2005)Google Scholar
  25. 25.
    Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV (2015)Google Scholar
  26. 26.
    Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: ICML (2016)Google Scholar
  27. 27.
    Ramamoorthi, R., Hanrahan, P.: An efficient representation for irradiance environment maps. In: SIGGRAPH Annual Conference on Computer Graphics and Interactive Techniques, pp. 497–500 (2001)Google Scholar
  28. 28.
    Ren, W., Yang, J., Deng, S., Wipf, D., Cao, X., Tong, X.: Face video deblurring via 3D facial priors. In: ICCV (2019)Google Scholar
  29. 29.
    Shen, Z., Lai, W., Xu, T., Kautz, J., Yang, M.: Deep semantic face deblurring. In: CVPR (2018)Google Scholar
  30. 30.
    Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: CVPR (2016)Google Scholar
  31. 31.
    Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: CVPR (2017)Google Scholar
  32. 32.
    Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., Nießner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: CVPR (2016)Google Scholar
  33. 33.
    Wang, X., Tang, X.: Hallucinating face by eigen transformation. Trans. Syst. Man Cybern. C 35(3), 425–434 (2005)CrossRefGoogle Scholar
  34. 34.
    Wang, X., Yu, K., Dong, C., Loy, C.: Recovering realistic texture in image super-resolution by deep spatial feature transform. In: CVPR (2018)Google Scholar
  35. 35.
    Yu, X., Fernando, B., Ghanem, B., Porikli, F., Hartley, R.: Face super-resolution guided by facial component heatmaps. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 219–235. Springer, Cham (2018). Scholar
  36. 36.
    Yu, X., Fernando, B., Hartley, R., Porikli, F.: Super-resolving very low-resolution face images with supplementary attributes. In: CVPR (2018)Google Scholar
  37. 37.
    Yu, X., Porikli, F.: Ultra-resolving face images by discriminative generative networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 318–333. Springer, Cham (2016). Scholar
  38. 38.
    Yu, X., Porikli, F.: Hallucinating very low-resolution unaligned and noisy face images by transformative discriminative autoencoders. In: CVPR (2017)Google Scholar
  39. 39.
    Yu, X., Porikli, F.: Imagining the unimaginable faces by deconvolutional networks. TIP 27(6), 2747–2761 (2018)MathSciNetzbMATHGoogle Scholar
  40. 40.
    Zafeiriou, S., Trigeorgis, G., Chrysos, G., Deng, J., Shen, J.: The menpo facial landmark localisation challenge: a step towards the solution. In: CVPRW (2017)Google Scholar
  41. 41.
    Zhang, K., et al.: Super-identity convolutional neural network for face hallucination. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 196–211. Springer, Cham (2018). Scholar
  42. 42.
    Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 294–310. Springer, Cham (2018). Scholar
  43. 43.
    Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. In: CVPR (2018)Google Scholar
  44. 44.
    Zhao, J., Xiong, L., Li, J., Xing, J., Yan, S., Feng, J.: 3D-aided dual-agent GANs for unconstrained face recognition. TPAMI 41, 2380–2394 (2019)CrossRefGoogle Scholar
  45. 45.
    Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face recognition: a literature survey. ACM Comput. Surv. (CSUR) 35(4), 399–458 (2003)CrossRefGoogle Scholar
  46. 46.
    Zhou, E., Fan, H.: Learning face hallucination in the wild. In: AAAI (2015)Google Scholar
  47. 47.
    Zhu, S., Liu, S., Loy, C.C., Tang, X.: Deep cascaded bi-network for face hallucination. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 614–630. Springer, Cham (2016). Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Informatics, Technische Universität MünchenMunichGermany
  2. 2.SKLOIS, IIE, CASBeijingChina
  3. 3.Harbin Institute of TechnologyHarbinChina
  4. 4.NJUSTNanjingChina
  5. 5.Tencent AI LabBellevueUSA
  6. 6.Peng Cheng Laboratory, Cyberspace Security Research CenterShenzhenChina

Personalised recommendations