Masked 3D conditional generative adversarial network for rock mesh generation

Article
  • 72 Downloads

Abstract

3D-GAN (Wu et al. in: Advances in Neural Information Processing Systems, pp. 82–90, 2016) has been introduced as a novel way to generate 3D models. In this paper, we propose a 3D-Masked-CGAN approach to apply in the generation of irregular 3D mesh geometry such as rocks. While there are many ways to generate 3D objects, the generation of irregular 3D models has its own peculiarity. To make a model realistic is extremely time-consuming and in high cost. In order to control the shape of generated 3D models, we extend 3D-GAN by adding conditional information into both the generator and discriminator. It is shown that that this model can generate 3D rock models with effective control over the shapes of generated models.

Keywords

GAN Computer vision Machine learning 3D rock model generation 

Notes

Acknowledgement

This work is supported by Sichuan Sci-Tech Support Plan, item number: 2017GZ0025, 2017GZ0321, 2016GZ0313.

References

  1. 1.
    Visualization, I.D.: Inc., speedtree. I, (2010)Google Scholar
  2. 2.
    Lim, J.J., Pirsiavash, H., Torralba, A.: Parsing IKEA objects: fine pose estimation. In: ICCV (2013)Google Scholar
  3. 3.
    Smith, E., Meger, D.: Improved adversarial systems for 3d object generation and reconstruction (2017). CoRR http://arxiv.org/abs/1707.09557. 1
  4. 4.
    Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3d generative adversarial modeling. In: Advances in Neural Information Processing Systems, pp. 82–90 (2016)Google Scholar
  5. 5.
    Meetshah: meetshah1995/tf-3dgan, Jul 2017. https://github.com/meetshah1995/tf-3dgan (1995)
  6. 6.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014). CoRR abs/1411.1784. http://arxiv.org/abs/1411.1784
  7. 7.
    Carlson, W.E.: An algorithm and data structure for 3d object synthesis using surface patch intersections. ACM SIGGRAPH Comput. Graph. 16(3), 255–263 (1982)CrossRefGoogle Scholar
  8. 8.
    Buhmann, J.M., Fellner, D.W., Held, M., Ketterer, J., Puzicha, J.: Dithered color quantization. Comput. Graph. Forum 17, 3, C219–C231 (1998). (Proc. Eurographics’98) http://diglib.eg.org/EG/CGF/volume17/issue3/ColQuant98.  https://doi.org/10.1111/1467-8659.00269
  9. 9.
    Chaudhuri, S., Kalogerakis, E., Guibas, L., Koltun, V.: Probabilistic reasoning for assembly-based 3d modeling. In: ACM Transactions on Graphics (TOG), vol. 30, p. 35. ACM (2011)Google Scholar
  10. 10.
    Funkhouser, T., Kazhdan, M., Shilane, P., Min, P., Kiefer, W., Tal, A., Rusinkiewicz, S., Dobkin, D.: Modeling by example. In: ACM Transactions on Graphics (TOG), vol. 23, pp. 652–663. ACM (2004)Google Scholar
  11. 11.
    Kreavoy, V., Julius, D., Sheffer, A.: Model composition from interchangeable components. In: 15th Pacific Conference on Computer Graphics and Applications, 2007. PG’07, pp. 129–138. IEEE (2007)Google Scholar
  12. 12.
    Merrell, P., Schkufza, E., Koltun, V.: Computergenerated residential building layouts. In: ACM Transactions on Graphics (TOG), vol. 29, p. 181. ACM (2010)Google Scholar
  13. 13.
    Peytavie, A., Galin, E., Grosjean, J., Mérillou, S.: Procedural generation of rock piles using aperiodic tiling. In: Computer Graphics Forum, vol. 28, pp. 1801–1809. Wiley (2009)Google Scholar
  14. 14.
    Hnaidi, H., Guérin, E., Akkouche, S., Peytavie, A., Galin, E.: Feature based terrain generation using diffusion equation. In: Computer Graphics Forum (2010), vol. 29, pp. 2179–2186. WileyGoogle Scholar
  15. 15.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  16. 16.
    Smith, E., Meger, D.: Improved adversarial systems for 3d object generation and reconstruction (2017). arXiv preprint arXiv:1707.09557
  17. 17.
    Yang, B., Wen, H., Wang, S., Clark, R., Markham, A., Trigoni, N.: 3d object reconstruction from a single depth view with adversarial learning (2017). arXiv preprint arXiv:1708.07969
  18. 18.
    Gulin, A., Digne, J., Galin, Ã., Peytavie, A., Wolf, C., Benes, B., Martinez, B.: Interactive example-based terrain authoring with conditional generative adversarial networks. ACM Trans. Graph. 36(6), 228 (2017).  https://doi.org/10.1145/3130800 CrossRefGoogle Scholar
  19. 19.
  20. 20.
    Geiss, R.: Generating complex procedural terrains using the gpu. GPU Gems 3, 7–37 (2007)Google Scholar
  21. 21.
    Halbritter, S.: Generative adversarial networksGoogle Scholar
  22. 22.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets (2014). arXiv preprint arXiv:1411.1784
  23. 23.
    Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3d surface construction algorithm. In: ACM Siggraph Computer Graphics, vol. 21, pp. 163–169. ACM (1987)Google Scholar
  24. 24.
    SP4CERAT: sp4cerat/fast-quadric-mesh-simplification. https://github.com/sp4cerat/Fast-Quadric-Mesh-Simplification (2016)
  25. 25.
    Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of Electronic Science and Technology of ChinaChengduChina

Personalised recommendations