Skip to main content
Springer Nature Link
Log in

LAGAN: Landmark Aided Text to Face Sketch Generation

  • Conference paper
  • First Online:
Pattern Recognition and Computer Vision (PRCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13537))

Included in the following conference series:

  • 1760 Accesses

Abstract

Face sketch is a concise representation of the human face, and it has a variety of applications in criminal investigation, biometrics, and social entertainment. It is well known that facial attribute is an underlying representation of the facial description. However, generating vivid face sketches, especially sketches with rich details, from given facial attributes text is still a challenging task as the text information is limited. Existing work synthetic face sketch is not realistic, especially the facial areas are not natural enough, even distorted. We aim to relieve the situation by introducing face prior knowledge, such as landmarks. This paper proposes a method, called LAGAN, that Landmark Aided Text to Face Sketch Generation. Specifically, we design a novel scale translation-invariant similarity loss based on the facial landmarks. It can measure the mutual similarity between real sketch and synthetic sketch and also measure the self similarity based on the symmetry of face attributes. Further to counter data deficiency, we construct a novel facial attribute text to sketch dataset called TextCUFSF with CUFSF face sketch dataset. Each sketch has 4 manual annotations. Qualitative and quantitative experiments demonstrate the effectiveness of our proposed method for sketch synthesis with attribute text. The code and data are available: https://github.com/chaowentao/LAGAN.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)

  2. Chang, L., Zhou, M., Han, Y., Deng, X.: Face sketch synthesis via sparse representation. In: ICPR, pp. 2146–2149 (2010)

    Google Scholar 

  3. Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: CVPR, pp. 8789–8797 (2018)

    Google Scholar 

  4. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248–255 (2009)

    Google Scholar 

  5. Di, X., Patel, V.M.: Face synthesis from visual attributes via sketch using conditional vaes and gans. arXiv preprint arXiv:1801.00077 (2017)

  6. Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS, pp. 2672–2680 (2014)

    Google Scholar 

  7. Gorti, S.K., Ma, J.: Text-to-image-to-text translation using cycle consistent adversarial networks. arXiv preprint arXiv:1808.04538 (2018)

  8. Han, H., Jain, A.K., Wang, F., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. TPAMI 40(11), 2597–2609 (2017)

    Article  Google Scholar 

  9. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)

  10. Klare, B.F., Klum, S., Klontz, J.C., Taborsky, E., Akgul, T., Jain, A.K.: Suspect identification based on descriptive facial attributes. In: IJCB, pp. 1–8 (2014)

    Google Scholar 

  11. Kurach, K., Lucic, M., Zhai, X., Michalski, M., Gelly, S.: The GAN landscape: losses, architectures, regularization, and normalization (2018). CoRR abs/1807.04720

    Google Scholar 

  12. Li, B., Qi, X., Lukasiewicz, T., Torr, P.H.: Controllable text-to-image generation. In: NeurIPS, pp. 2065–2075 (2019)

    Google Scholar 

  13. Liao, W., Hu, K., Yang, M.Y., Rosenhahn, B.: Text to image generation with semantic-spatial aware GAN. arXiv preprint arXiv:2104.00567 (2021)

  14. Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are gans created equal? a large-scale study. arXiv preprint arXiv:1711.10337 (2017)

  15. Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)

  16. Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)

  17. Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML, pp. 1060–1069 (2016)

    Google Scholar 

  18. Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: NeurIPS, pp. 217–225 (2016)

    Google Scholar 

  19. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS, pp. 2234–2242 (2016)

    Google Scholar 

  20. Sangkloy, P., Lu, J., Fang, C., Yu, F., Hays, J.: Scribbler: controlling deep image synthesis with sketch and color. In: CVPR, pp. 6836–6845 (2017)

    Google Scholar 

  21. Shen, W., Liu, R.: Learning residual images for face attribute manipulation. In: CVPR, pp. 1225–1233 (2017)

    Google Scholar 

  22. Song, L., Lu, Z., He, R., Sun, Z., Tan, T.: Geometry guided adversarial facial expression synthesis. arXiv preprint arXiv:1712.03474 (2017)

  23. Song, Y., Bao, L., Yang, Q., Yang, M.-H.: Real-time exemplar-based face sketch synthesis. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 800–813. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_51

    Chapter  Google Scholar 

  24. Sun, R., Huang, C., Shi, J., Ma, L.: Mask-aware photorealistic face attribute manipulation. arXiv preprint arXiv:1804.08882 (2018)

  25. Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1–9 (2015)

    Google Scholar 

  26. Tan, Y., Tang, L., Wang, X.: An improved criminisi inpainting algorithm based on sketch image. J. Comput. Theor. Nanosci. 14(8), 3851–3860 (2017)

    Article  Google Scholar 

  27. Tang, X., Wang, X.: Face sketch recognition. TCSVT 14(1), 50–57 (2004)

    Google Scholar 

  28. Tao, M., et al.: DF-GAN: a simple and effective baseline for text-to-image synthesis. arXiv preprint arXiv:2008.05865 (2020)

  29. Tome, P., Vera-Rodriguez, R., Fierrez, J., Ortega-Garcia, J.: Facial soft biometric features for forensic face recognition. Forensic Sci. Int. 257, 271–284 (2015)

    Article  Google Scholar 

  30. Wang, N., Gao, X., Sun, L., Li, J.: Bayesian face sketch synthesis. TIP 26(3), 1264–1274 (2017)

    MathSciNet  MATH  Google Scholar 

  31. Wang, N., Li, J., Sun, L., Song, B., Gao, X.: Training-free synthesized face sketch recognition using image quality assessment metrics. arXiv preprint arXiv:1603.07823 (2016)

  32. Wang, N., Tao, D., Gao, X., Li, X., Li, J.: A comprehensive survey to face hallucination. IJCV 106(1), 9–30 (2014)

    Article  Google Scholar 

  33. Wang, X., Tang, X.: Face photo-sketch synthesis and recognition. TPAMI 31(11), 1955–1967 (2008)

    Article  Google Scholar 

  34. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600–612 (2004)

    Google Scholar 

  35. Xiong, X., Torre, F.D.L.: Supervised descent method and its applications to face alignment. In: CVPR, pp. 532–539 (2013)

    Google Scholar 

  36. Xu, T., et al.: Attngan: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR, pp. 1316–1324 (2018)

    Google Scholar 

  37. Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776–791. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_47

    Chapter  Google Scholar 

  38. Yi, Z., Zhang, H., Tan, P., Gong, M.: Dualgan: unsupervised dual learning for image-to-image translation. In: ICCV, pp. 2868–2876 (2017)

    Google Scholar 

  39. Yuan, M., Peng, Y.: Text-to-image synthesis via symmetrical distillation networks. arXiv preprint arXiv:1808.06801 (2018)

  40. Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: ICML, pp. 7354–7363. PMLR (2019)

    Google Scholar 

  41. Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. arXiv preprint arXiv:1710.10916 (2017)

  42. Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV, pp. 5907–5915 (2017)

    Google Scholar 

  43. Zhang, M., Wang, N., Li, Y., Wang, R., Gao, X.: Face sketch synthesis from coarse to fine. In: AAAI, pp. 7558–7565 (2018)

    Google Scholar 

  44. Zhang, W., Wang, X., Tang, X.: Coupled information-theoretic encoding for face photo-sketch recognition. In: CVPR, pp. 513–520. IEEE (2011)

    Google Scholar 

  45. Zou, C., et al.: SketchyScene: richly-annotated scene sketches. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 438–454. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01267-0_26

    Chapter  Google Scholar 

Download references

Acknowledgement

This work was supported by the National Key Research and Development Program of China under grant No. 2019YFC1521104, Natural Science Foundation of China (61772050, 62172247).

Author information

Authors and Affiliations

  1. Beijing Normal University, Beijing, China

    Wentao Chao, Liang Chang, Fangfang Xi & Fuqing Duan

Authors
  1. Wentao Chao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Liang Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fangfang Xi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fuqing Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liang Chang .

Editor information

Editors and Affiliations

  1. Southern University of Science and Technology, Shenzhen, China

    Shiqi Yu

  2. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Zhaoxiang Zhang

  3. Hong Kong Baptist University, Hong Kong, China

    Pong C. Yuen

  4. Northwestern Polytechnical University, Xi'an, China

    Junwei Han

  5. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Tieniu Tan

  6. Hong Kong Baptist University, Hong Kong, China

    Yike Guo

  7. Sun Yat-sen University, Guangzhou, China

    Jianhuang Lai

  8. Southern University of Science and Technology, Shenzhen, China

    Jianguo Zhang

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chao, W., Chang, L., Xi, F., Duan, F. (2022). LAGAN: Landmark Aided Text to Face Sketch Generation. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13537. Springer, Cham. https://doi.org/10.1007/978-3-031-18916-6_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-18916-6_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-18915-9

  • Online ISBN: 978-3-031-18916-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics