Abstract
Facial expression synthesis (FES) is to generate a new face with a desired expression domain. However, in FES field, many current methods fail to enable relevant facial components to transform simultaneously, which makes the target expression look unnatural. Therefore, we are purposed to develop a method which can edit main organs synchronously when generating a new expression. Based on this, the global spatial interaction mechanism is introduced by us which can capture the long-range dependency between distant positions. Besides, current methods usually suffer from blurs and artifacts around key regions. From the point of frequency domain, it is probably caused by the distortion of high frequency information. After this we add a spectrum restriction loss to original training losses in order to improve the fidelity of generated faces. Extensive experiments prove our model a great success on two widely-used datasets: MUG and CASIA-Oulu.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Deng, Z., Noh, J.: Computer facial animation: a survey. In: Deng, Z., Neumann, U. (eds.) Data-Driven 3D Facial Animation, pp. 1–28. Springer, London (2008). https://doi.org/10.1007/978-1-84628-907-1_1
Liu, Z., Ying, S., Zhang, Z.: Expressive expression mapping with ratio images. In: 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 271–276. Association for Computing Machinery (2001)
Lewis, J.P., Cordner, M., Fong, N.: Pose space deformation: a unified approach to shape interpolation and skeleton-driven deformation. In: 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 165–172. Association for Computing Machinery (2000)
Goodfellow, I., et al.: Generative adversarial networks. In: Advances in Neural Information Processing Systems, pp. 2672–2680. MIT Press (2014)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: A unified approach to shape interpolation and skeleton-driven deformation. In: 7th International Conference on Learning Representations, pp. 165–172. Elsevier (2019)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: 37th Conference on Computer Vision and Pattern Recognition, pp. 4401–4410. IEEE (2019)
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: 35th Conference on Computer Vision and Pattern Recognition, pp. 4681–4690. IEEE (2017)
Zheng, W., Ye, M., Fan, Y., Xiang, B., Satoh, S.: Cascaded SR-GAN for scale-adaptive low resolution person re-identification. In: 27th International Joint Conference on Artificial Intelligence, pp. 4–11. Morgan Kaufmann (2018)
Huang, R., Zhang, S., Li, T., He, R.: Beyond face rotation: global and local perception GAN for photo-realistic and identity preserving frontal view synthesis. In: Computer Society, pp. 2439–2448. IEEE (2017)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. In: Computer Science, pp. 2672–2680. IEEE (2014)
Choi, Y., Choi, M., Kim, M., Ha, J.W., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: 36th Conference on Computer Vision and Pattern Recognition, pp. 8789–8797. IEEE (2018)
Geng, Z., Cao, C., Tulyakov, S.: 3D guided fine-grained face manipulation. In: 37th Conference on Computer Vision and Pattern Recognition, pp. 9821–9830. IEEE (2019)
Pumarola, A., Agudo, A., Martinez, A.M., Sanfeliu, A., Moreno-Noguer, F.: Ganimation: anatomically-aware facial animation from a single image. In: 15th the European Conference on Computer Vision, pp. 818–833. IEEE (2018)
Ding, H., Sricharan, K., Chellappa, R.: ExprGAN: facial expression editing with controllable expression intensity. In: 2nd the Association for the Advance of Artificial Intelligence, pp. 748–758. AAAI (2018)
Song, L., Lu, Z., He, R., Sun, Z., Tan, T.: Geometry guided adversarial facial expression synthesis. In: 26th ACM International Conference on Multimedia, pp. 627–635. Association for Computing Machinery (2018)
Wang, X., Girshick, R., Gupta, A.: Non-local neural networks. In: 36th Conference on Computer Vision and Pattern Recognition, pp. 7794–7803. IEEE (2018)
Durall, R., Keuper, M., Keuper, J.: Watch your up-convolution. In: 38th Conference on Computer Vision and Pattern Recognition, pp. 7890–7899. IEEE (2020)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 34th Conference on Computer Vision and Pattern Recognition, pp. 1125–1134. IEEE (2016)
Acknowledgements
We would like to appreciate anonymous reviewers for spending time on our work. This work was supported by the National Natural Science Foundation of China under Grant 62076131.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Dai, J. (2021). Facial Expression Synthesis with Synchronous Editing of Face Organs. In: Feng, J., Zhang, J., Liu, M., Fang, Y. (eds) Biometric Recognition. CCBR 2021. Lecture Notes in Computer Science(), vol 12878. Springer, Cham. https://doi.org/10.1007/978-3-030-86608-2_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-86608-2_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86607-5
Online ISBN: 978-3-030-86608-2
eBook Packages: Computer ScienceComputer Science (R0)