Skip to main content
SpringerLink
Log in

Exp-GAN: 3D-Aware Facial Image Generation with Expression Control

  • Conference paper
  • First Online:
Computer Vision – ACCV 2022 (ACCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13847))

Included in the following conference series:

Abstract

This paper introduces Exp-GAN, a 3D-aware facial image generator with explicit control of facial expressions. Unlike previous 3D-aware GANs, Exp-GAN supports fine-grained control over facial shapes and expressions disentangled from poses. To this ends, we propose a novel hybrid approach that adopts a 3D morphable model (3DMM) with neural textures for the facial region and a neural radiance field (NeRF) for non-facial regions with multi-view consistency. The 3DMM allows fine-grained control over facial expressions, whereas the NeRF contains volumetric features for the non-facial regions. The two features, generated separately, are combined seamlessly with our depth-based integration method that integrates the two complementary features through volume rendering. We also propose a training scheme that encourages generated images to reflect control over shapes and expressions faithfully. Experimental results show that the proposed approach successfully synthesizes realistic view-consistent face images with fine-grained controls. Code is available at https://github.com/kakaobrain/expgan.

This work was done when the first author was with Kookmin University.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Abdal, R., Zhu, P., Mitra, N.J., Wonka, P.: StyleFlow: attribute-conditioned exploration of StyleGAN-generated images using conditional continuous normalizing flows. ACM Trans. Graph. (Proc. SIGGRAPH 2021) 40(3) (2021)

    Google Scholar 

  2. Bühler, M.C., Meka, A., Li, G., Beeler, T., Hilliges, O.: VariTex: variational neural face textures. In: Proceedings of ICCV, pp. 13890–13899 (2021)

    Google Scholar 

  3. Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of CVPR, pp. 16123–16133 (2022)

    Google Scholar 

  4. Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3D-aware image synthesis. In: Proceedings of CVPR, pp. 5799–5809 (2021)

    Google Scholar 

  5. Chen, A., Liu, R., Xie, L., Chen, Z., Su, H., Yu, J.: SofGAN: a portrait image generator with dynamic styling. ACM Trans. Graph. 42(1), 1–26 (2022)

    Google Scholar 

  6. Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of CVPR, pp. 4690–4699 (2019)

    Google Scholar 

  7. Deng, Y., Yang, J., Chen, D., Wen, F., Tong, X.: Disentangled and controllable face image generation via 3D imitative-contrastive learning. In: Proceedings of CVPR, pp. 5154–5163 (2020)

    Google Scholar 

  8. Deng, Y., Yang, J., Xiang, J., Tong, X.: GRAM: generative radiance manifolds for 3D-aware image generation. In: Proceedings of CVPR, pp. 10673–10683 (2022)

    Google Scholar 

  9. Feng, Y., Feng, H., Black, M.J., Bolkart, T.: Learning an animatable detailed 3D face model from in-the-wild images. ACM Trans. Graph. (Proc. SIGGRAPH 2021) 40(8), Article No. 88 (2021)

    Google Scholar 

  10. Ghosh, P., Gupta, P.S., Uziel, R., Ranjan, A., Black, M., Bolkart, T.: GIF: generative interpretable faces. In: Proceedings of 3DV, pp. 868–878 (2020)

    Google Scholar 

  11. Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of NIPS, pp. 2672–2680 (2014)

    Google Scholar 

  12. Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3D-aware generator for high-resolution image synthesis. In: Proceedings of ICLR (2022)

    Google Scholar 

  13. Härkönen, E., Hertzmann, A., Lehtinen, J., Paris, S.: GANSpace: discovering interpretable GAN controls. In: Proceedings of NeurIPS (2020)

    Google Scholar 

  14. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of NIPS, pp. 6629–6640 (2017)

    Google Scholar 

  15. Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of CVPR, pp. 4401–4410 (2019)

    Google Scholar 

  16. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of CVPR, pp. 8110–8119 (2020)

    Google Scholar 

  17. Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Proceedings of ICLR (2014)

    Google Scholar 

  18. Kowalski, M., Garbin, S.J., Estellers, V., Baltrušaitis, T., Johnson, M., Shotton, J.: CONFIG: controllable neural face image generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 299–315. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_18

    Chapter  Google Scholar 

  19. Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. (Proc. SIGGRAPH Asia 2017) 36(4), Article No. 194 (2017)

    Google Scholar 

  20. Ma, S., et al.: Pixel codec avatars. In: Proceedings of CVPR, pp. 64–73 (2021)

    Google Scholar 

  21. Mescheder, L., Geiger, A., Nowozin, S.: Which Training Methods for GANs do actually Converge? arXiv preprint arXiv:1801.04406 (2018)

  22. Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24

    Chapter  Google Scholar 

  23. Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: HoloGAN: unsupervised learning of 3D representations from natural images. In: Proceedings of ICCV, pp. 7588–7597 (2019)

    Google Scholar 

  24. Paysan, P., Knothe, R., Amberg, B., Romdhani, S., Vetter, T.: A 3D face model for pose and illumination invariant face recognition. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 296–301 (2009)

    Google Scholar 

  25. Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3D-aware image synthesis. In: Proceedings of NeurIPS (2020)

    Google Scholar 

  26. Shen, Y., Gu, J., Tang, X., Zhou, B.: Interpreting the latent space of GANs for semantic face editing. In: Proceedings of CVPR, pp. 9243–9252 (2020)

    Google Scholar 

  27. Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in GANs. In: Proceedings of CVPR, pp. 1532–1540 (2021)

    Google Scholar 

  28. Shoshan, A., Bhonker, N., Kviatkovsky, I., Medioni, G.: GAN-control: explicitly controllable GANs. In: Proceedings of ICCV, pp. 14083–14093 (2021)

    Google Scholar 

  29. Sitzmann, V., Martel, J.N.P., Bergman, A., Lindell, D.B., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: Proceedings of NeurIPS (2020)

    Google Scholar 

  30. Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of ICML (2015)

    Google Scholar 

  31. Tewari, A., et al.: StyleRig: rigging StyleGAN for 3D control over portrait images. In: Proceedings of CVPR, pp. 6142–6151 (2020)

    Google Scholar 

  32. Thies, J., Zollhöfer, M., Nießner, M.: Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. (Proc. SIGGRAPH 2019) 38(4) (2019)

    Google Scholar 

  33. Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of CVPR, pp. 4690–4699 (2021)

    Google Scholar 

  34. Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: Proceedings of CVPR, pp. 12863–12872 (2021)

    Google Scholar 

  35. Zhou, P., Xie, L., Ni, B., Tian, Q.: CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis. arXiv preprint arXiv:2110.09788 (2021)

Download references

Acknowledgements

This was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2022R1F1A1074628, 2022R1A5A7000765) and Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2020-0-01826, Problem-Based Learning Program for Researchers to Proactively Solve Practical AI Problems (Kookmin University) and No. 2019-0-01906, Artificial Intelligence Graduate School Program (POSTECH)).

Author information

Authors and Affiliations

  1. Kakao Brain, Seongnam, South Korea

    Yeonkyeong Lee, Taeho Choi & Hyunjoon Lee

  2. Kookmin University, Seoul, South Korea

    Hyunsung Go & Junho Kim

  3. POSTECH, Pohang, South Korea

    Sunghyun Cho

Authors
  1. Yeonkyeong Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Taeho Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hyunsung Go
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hyunjoon Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sunghyun Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Junho Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Junho Kim .

Editor information

Editors and Affiliations

  1. University of Wollongong, Wollongong, NSW, Australia

    Lei Wang

  2. University of Bonn, Bonn, Germany

    Juergen Gall

  3. University of Adelaide, Adelaide, SA, Australia

    Tat-Jun Chin

  4. National Institute of Informatics, Tokyo, Japan

    Imari Sato

  5. Johns Hopkins University, Baltimore, MD, USA

    Rama Chellappa

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 42455 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Lee, Y., Choi, T., Go, H., Lee, H., Cho, S., Kim, J. (2023). Exp-GAN: 3D-Aware Facial Image Generation with Expression Control. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13847. Springer, Cham. https://doi.org/10.1007/978-3-031-26293-7_10

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26293-7_10

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26292-0

  • Online ISBN: 978-3-031-26293-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation