Abstract
Neural Style Transfer has been successfully applied in the creative process for generating novel artistic 2D images by transferring the style of a painting to an existing content image. These techniques which rely on deep neural networks have been extended to further computational creativity tasks like video, motion and animation stylization. However, only few research has been conducted to utilize Neural Style Transfer in the spatially three-dimensional space. Existing 2D/3D hybrid approaches avoid the extra dimension during the stylization process and add postprocessing or differentiable rendering to transform the results to 3D. In this paper, we propose for the first time a complete three-dimensional Neural Style Transfer pipeline based on a high-resolution voxel representation. Following our previous research, our architecture includes the standardized gram matrix style loss for noise reduction and visual improvement, the bipolar exponential activation function for symmetric feature distributions and best practices for the underlying classification network. In addition, we propose regularization terms for voxel-based 3D Neural Style Transfer optimization and demonstrate their capability to significantly reduce noise and undesired artefacts. We apply our 3D Neural Style Transfer pipeline on a set of style targets. The style transfer results are evaluated using 3D shape descriptors which confirm the subjective visual improvements.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
http://www.github.com/HRI-EU (code accessible following positive reviews).
- 2.
References
Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414–2423 (2016)
Friedrich, T., Schmitt, S., Menzel, S.: Rapid creation of vehicle line-ups by eigenspace projections for style transfer. In: Proceedings of the Design Society: DESIGN Conference, pp. 867–876 (2020)
Jing, Y., Yang, Y., Feng, Z., Ye, J., Song, M.: Neural style transfer: a review, CoRR, vol. abs/1705.04058 (2017)
Holden, D., Habibie, I., Kusajima, I., Komura, T.: Fast neural style transfer for motion data. IEEE Comput. Graphics Appl. 37(4), 42–49 (2017)
Friedrich, T., Aulig, N., Menzel, S.: On the potential and challenges of neural style transfer for three-dimensional shape data. In: Rodrigues, H.C., et al. (eds.) EngOpt 2018, pp. 581–592. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-97773-7_52
Friedrich, T., Menzel, S.: Standardization of gram matrix for improved 3D neural style transfer. In: Proceedings of IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1375–1382 (2019)
Friedrich, T., Wollstadt, P., Menzel, S.: The effects of non-linear operators in voxel-based deep neural networks for 3D style reconstruction. In: Proceedings of 2020 IEEE Symposium Series on Computational Intelligence (SSCI) ,pp. 1460–1468. IEEE (2020)
Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes, In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07–12-June-2015, pp. 1912–1920 (2015)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of 3rd International Conference on Learning Representations (ICLR) (2015)
Huang, E., Gupta, S.: Style is a Distribution of Features. arXiv:2007.13010 (2020)
Ma, C., Huang, H., Sheffer, A., Kalogerakis, E., Wang, R.: Analogy- driven 3d style transfer. Computer Graphics Forum, vol. 33, no. 2. Wiley Online Library, pp. 175–184 (2014)
Ren, Y., Zheng, H.: The Spire of AI - Voxel-based 3D neural style transfer. In: Proceedings of the 25th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA) (2020)
Kato, H., Ushiku, Y., Harada, T.: Neural 3D mesh renderer. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3907–3916 (2018)
Sýkora, D., Jamriška, O., Lu, J., Shechtman, E.: StyleBlit: fast example-based stylization with local guidance. Comput. Graph. Forum 38(2), 83–91 (2018)
Kim, B., Azevedo, V.C., Gross, M., Solenthaler, B.: Transport-based neural style transfer for smoke simulations. ACM Trans. Graph. 38(6) (2019)
Qi, C.R., Su, H., Niebner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data, In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, pp. 5648–5656 (2016)
Understanding Formal Analysis. http://www.getty.edu/education/teachers/building_lessons/formal_analysis.htm. Accessed on 01 July 2020
Maturana, D., Scherer, S.: VoxNet: A 3D Convolutional Neural Network for real-time object recognition, In: Proceedings of IEEE International Conference on Intelligent Robots and Systems, vol. 2015-Dec, pp. 922–928 (2015)
Eidnes, L., Nøkland, A.: Shifting Mean Activation Towards Zero with Bipolar Activation Functions. arXiv:1709.04054 (2017)
Lara López, G., Peña Pérez Negrón, A., De Antonio Jiménez, A., RamÃrez RodrÃguez, J., Imbert Paredes, R.: Comparative analysis of shape descriptors for 3D objects. Multimedia Tools Appl. 76(5), 6993–7040 (2017)
Rubner, Y., Tomasi, C., Guibas, L. J.: A metric for distributions with applications to image databases. In: Proceedings of International Conference on Computer Vision (ICCV), pp. 59–66 (1998)
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
Friedrich, T., Hammer, B., Menzel, S. (2021). Voxel-Based Three-Dimensional Neural Style Transfer. In: Rojas, I., Joya, G., Català , A. (eds) Advances in Computational Intelligence. IWANN 2021. Lecture Notes in Computer Science(), vol 12861. Springer, Cham. https://doi.org/10.1007/978-3-030-85030-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-85030-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85029-6
Online ISBN: 978-3-030-85030-2
eBook Packages: Computer ScienceComputer Science (R0)