Abstract
The article proposes a method of combining multiple deep forward neural networks to generate a distribution of objects in a 2D scene. The main concepts of machine learning, neural networks and procedural content generation concerning this intention are presented here. Additionally, these concepts are put into the context of computer graphics and used in a practical example of generating an indoor 2D scene. A method of vectorization of input datasets for training forward neural networks is proposed. Scene generation is based on the consequent placement of objects of different classes into the free space defining a room of a certain shape. Several evaluate methods have been proposed for testing the correctness of generation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M. et al.: TensorFlow: A system for large-scale machine learning. In: Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, pp. 21–28. Savannah USENIX Association, ISBN 978-1-931971-33-1. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf (2016). Accessed 20 Feb 2020
Goodfellow, I. et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M. (eds.) Advances in Neural Information Processing Systems, pp. 2672–2680. Curran Associates, http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf (2016). Accessed 20 Feb 2020
Jebara, T.: Machine Learning Discriminative and Generative. Springer, USA (2004)
Goodfellow, I.: Tutorial: Generative Adversarial Networks. In: NIPS, http://arxiv.org/abs/1701.00160 (2016). Accessed 20 Feb 2020
Suarez, P.L., Sappa, A.D., Victimilla, B.X.: Infrared image colorization based on a triplet DCGAN architecture. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 212–217, Honolulu, HI, USA (2017). ISBN: 978-1-5386-0733-6. https://doi.org/10.1109/cvprw.2017.32
Isola, P., Zhou, J.Y., Efros, T.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (2016). ISBN: 978-1-5386-0457-1. http://arxiv.org/abs/1611.07004
Summerwille, A. et al.: Content Generation via Machine Learning (PCGML). http://arxiv.org/abs/1702.00539 (2017). Accessed 20 Feb 2020
Summerwille, A., Mateas, M.: Super Mario as a string: Platformer level generation via LSTMs. http://arxiv.org/abs/1603.00930 (2016). Accessed 20 Feb 2020
Jain, R., Isaksen, A., Holmga, C., Togelius, J.: Autoencoders for level generation, repair, and recognition. In: Proceedings of the ICCC Workshop on Computational Creativity and Games, p. 9 (2016)
Wick, Christoph: Deep learning. Informatik-Spektrum 40(1), 103–107 (2016). https://doi.org/10.1007/s00287-016-1013-2
Fisher, M. et al.: Example-based synthesis of 3D object arrangements. ACM Trans. Graph. 31(6), 1-11 (2012)
Giacomello, E., Lanzi, P., L., Loiacono, D.: DOOM level generation using generative adversarial networks. In: IEEE Games, Entertainment, Media Conference (GEM) (2018)
Beckham, C., Pal, C.: A step towards procedural terrain generation with GANs. http://arxiv.org/abs/1707.03383 (2017). Accessed 15 Mar 2019
Kenney: https://www.kenney.nl/assets (2019). Accessed 15 Mar 2019
Acknowledgments
This work and the contribution were supported by a project of Students Grant Agency (SPEV 2020) - FIM, University of Hradec Kralove, Czech Republic. The authors of this paper would like to thank Milan Košťák, a PhD student of Applied Informatics at the University of Hradec Kralove, for help with implementation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ježek, B., Ouhrabka, A., Slabý, A. (2020). Procedural Content Generation via Machine Learning in 2D Indoor Scene. In: De Paolis, L., Bourdot, P. (eds) Augmented Reality, Virtual Reality, and Computer Graphics. AVR 2020. Lecture Notes in Computer Science(), vol 12242. Springer, Cham. https://doi.org/10.1007/978-3-030-58465-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-58465-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58464-1
Online ISBN: 978-3-030-58465-8
eBook Packages: Computer ScienceComputer Science (R0)