Abstract
The realistic generation of synthetic 3D faces is an open challenge due to the complexity of the geometry and the lack of large and diverse publicly available datasets. Generative models based on convolutional neural networks (CNNs) have recently demonstrated great ability to produce novel synthetic high-resolution images indistinguishable from the original pictures by an expert human observer. However, applying them to non-grid-like data like 3D meshes presents many challenges. In our work, we overcome the challenges by first reducing the face mesh to a 2D regular image representation and then exploiting one prominent state-of-the-art generative approach. The approach uses a Vector Quantized Variational Autoencoder VQ-VAE-2 to learn a latent discrete representation of the 2D images. Then, the 3D synthesis is achieved by fitting the latent space and sampling it with an autoregressive model, PixelSNAIL. The quantitative and qualitative evaluation demonstrate that synthetic faces generated with our method are statistically closer to the real faces when compared to a classical synthesis approach based on Principal Component Analysis (PCA).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, S.-L., Liu, Y., Dong, L.-F., Tong, X.: RAS: a data-driven rigidity-aware skinning model for 3D facial animation. In: Computer Graphics Forum, pp. 581–594 (2020)
Carrigan, E., Zell, E., Guiard, C., McDonnell, R.: Expression packing: as-few-as-possible training expressions for blendshape transfer. In: Computer Graphics Forum, pp. 219–233 (2020)
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. 36, 191–194 (2017)
Valev, H., Gallucci, A., Leufkens, T., Westerink, J., Sas, C.: Applying delaunay triangulation augmentation for deep learning facial expression generation and recognition. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12663, pp. 730–740. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68796-0_53
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)
Varol, G., et al.: Learning from synthetic humans. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 109–117 (2017)
Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187–194 (1999)
Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P.: Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34, 18–42 (2017)
Ranjan, A., Bolkart, T., Sanyal, S., Black, M.J.: Generating 3D faces using convolutional mesh autoencoders. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 725–741. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_43
De Haan, P., Weiler, M., Cohen, T., Welling, M.: Gauge equivariant mesh CNNs: anisotropic convolutions on geometric graphs. arXiv Prepr. arXiv2003.05425 (2020)
Zhang, S., Tong, H., Xu, J., Maciejewski, R.: Graph convolutional networks: a comprehensive review. Comput. Soc. Netw. 6(1), 1–23 (2019). https://doi.org/10.1186/s40649-019-0069-y
Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems, pp. 14837–14847 (2019)
Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747–1756 (2016)
den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et al.: Conditional image generation with pixelcnn decoders. In: Advances in Neural Information Processing Systems, pp. 4790–4798 (2016)
Vaswani, A., e al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)
Chen, X., Mishra, N., Rohaninejad, M., Abbeel, P.: PixelSNAIL: an improved autoregressive generative model. In: 35th International Conference on Machine Learning ICML 2018, vol. 2, pp. 1364–1372 (2018)
Davies, R., Twining, C., Taylor, C.: Statistical Models of Shape: Optimisation and Evaluation. Springer, London (2008). https://doi.org/10.1007/978-1-84800-138-1
Abrevaya, V.F., Boukhayma, A., Wuhrer, S., Boyer, E.: A decoupled 3D facial shape model by adversarial training. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9419–9428 (2019)
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., Nießner, M.: Face2face: real-time face capture and reenactment of RGB videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2387–2395 (2016)
Vlasic, D., Brand, M., Pfister, H., Popovic, J.: Face transfer with multilinear models. In: ACM SIGGRAPH 2006 Courses, pp. 24–es (2006)
Booth, J., Roussos, A., Zafeiriou, S., Ponniah, A., Dunaway, D.: A 3D morphable model learnt from 10,000 faces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5543–5552 (2016)
Tuan Tran, A., Hassner, T., Masi, I., Medioni, G.: Regressing robust and discriminative 3D morphable models with a very deep neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5163–5172 (2017)
Gu, X., Gortler, S.J., Hoppe, H.: Geometry images. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 355–361 (2002)
Booth, J., Zafeiriou, S.: Optimal UV spaces for facial morphable model construction. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 4672–4676 (2014)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214–223 (2017)
Slossberg, R., Shamai, G., Kimmel, R.: High quality facial surface and texture synthesis via generative adversarial networks. In: Leal-Taixé, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 498–513. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11015-4_36
Shamai, G., Slossberg, R., Kimmel, R.: Synthesizing facial photometries and corresponding geometries using generative adversarial networks. ACM Trans. Multimedia Comput. Commun. Appl. 15, 1–24 (2019)
Moschoglou, S., Ploumpis, S., Nicolaou, M.A., Papaioannou, A., Zafeiriou, S.: 3DFaceGAN: adversarial nets for 3D face representation, generation, and translation. Int. J. Comput. Vis. 128, 2534–2551 (2020)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: 2nd International Conference on Learning Representations ICLR 2014 - Conference Track Proceedings, pp. 1–14 (2014)
Bagautdinov, T., Wu, C., Saragih, J., Fua, P., Sheikh, Y.: Modeling facial geometry using compositional VAEs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3877–3886 (2018)
Abrevaya, V.F., Wuhrer, S., Boyer, E.: Multilinear autoencoder for 3D face model learning. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1–9 (2018)
Li, K., Liu, J., Lai, Y.-K., Yang, J.: Generating 3D faces using multi-column graph convolutional networks. In: Computer Graphics Forum, pp. 215–224 (2019)
Tam, G.K.L.L., et al.: Registration of 3D point clouds and meshes: a survey from rigid to Nonrigid. IEEE Trans. Vis. Comput. Graph. 19, 1199–1217 (2013)
van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. In: Eurographics Symposium on Geometry Processing (2011)
Gallucci, A., Znamenskiy, D., Petkovic, M.: Prediction of 3D body parts from face shape and anthropometric measurements. J. Image Graph. 8, 67–77 (2020)
van den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, pp. 6306–6315 (2017)
Kingma, D.P., Welling, M.: An introduction to variational autoencoders. arXiv Prepr. arXiv1906.02691 (2019)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Kabsch, W.: A solution for the best rotation to relate two sets of vectors. Acta Crystallogr. Sect. A Cryst. Phys. Diffr. Theor. Gen. Crystallogr. 32, 922–923 (1976)
Ball, R., Molenbroek, J.F.M.: Measuring Chinese heads and faces. In: Proceedings of the 9th International Congress of Physiological Anthropology, Human Diversity Design for Life, pp. 150–155 (2008)
Robinette, K.M., Daanen, H., Paquet, E.: The CAESAR project: a 3-D surface anthropometry survey. In: Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062), pp. 380–386 (1999)
Robinette, K.M., Daanen, H.: Lessons learned from CAESAR: a 3-D anthropometric survey, 5 (2003)
Gallucci, A., Pezzotti, N., Znamenskiy, D., Petkovic, M.: A latent space exploration for microscopic skin lesion augmentations with VQ-VAE-2 and PixelSNAIL. In: SPIE Medical Imaging Proceedings (2021)
Paszke, A., et al.: Automatic differentiation in PyTorch (2017)
Acknowledgments
We thank Philips Research for providing access to the datasets of facial scans and software resources to manage the high-resolution parametric models.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gallucci, A., Znamenskiy, D., Pezzotti, N., Petkovic, M. (2022). Generating High-Resolution 3D Faces Using VQ-VAE-2 with PixelSNAIL Networks. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds) Image Analysis and Processing. ICIAP 2022 Workshops. ICIAP 2022. Lecture Notes in Computer Science, vol 13374. Springer, Cham. https://doi.org/10.1007/978-3-031-13324-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-13324-4_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13323-7
Online ISBN: 978-3-031-13324-4
eBook Packages: Computer ScienceComputer Science (R0)