Generative Design applied to Cloud Modeling
Resumo
Geometric modeling has recently leveraged the power of Generative Design. Generative Design can be seen as a framework in which models can be generated by systematically exploring a space of shapes generated by recombination of parametric shape descriptors. In this work, we explore the use of Generative Design for modeling 3D clouds. Clouds are usually modeled in Computer Graphics as voxelized models by using a combination of implicit and procedural techniques. Hence, they are described by a large number of parameters. Although these parameters usually include parameters that define a combination of scalar fields, noise functions and affine transforms, the controlled use of such parameters is rather complex. How to tune them up to obtain a plausible result is not obvious. We propose a method based on generative design combined with Machine Learning to produce families of cloud shapes automatically. Our generative design method is based on an evolutionary approach that generates instances of plausible 3D cloud shapes by optimizing a fitness function that measures the likelihood of a shape be a cloud. As the manual design of a fitness function is also quite complex, we propose using a Convolutional Neural Network to learn the fitness of arbitrary 2D views of the generated clouds. We perform several experiments that confirm the viability of the proposed method compared to manually modeled clouds.
Referências
B. Wyvill and G. Wyvill. "Field functions for implicit surfaces," in New Trends in Computer Graphics, N. Magnenat-Thalman and D. Thalmann, Eds., Springer, 1988, pp. 328-338.
B. Lipuš and N. Guid. "A new implicit blending technique for volumetric modelling, " The Visual Computer, vol. 21, 2005, pp. 83–91.
K. Perlin. "An image synthesizer," in ACM Siggraph Computer Graphics, 1985, pp. 287–296.
J. Schpok, J. Simons, D. S. Ebert, and C. Hansen. "A real-time cloud modeling, rendering, and animation system," in Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation, Eurographics Association, 2003, pp. 160–166.
S. Khan, M. J. Awan. "A generative design technique for exploring shape variations," Advanced Engineering Informatics, vol. 38, 2018, pp. 712-724. doi: 10.1016/j.aei.2018.10.005.
V. Singh and N. Gu. "Towards an integrated generative design framework," Design Studies, vol. 33, no. 2, 2012, pp. 185-207, doi:10.1016/j.destud.2011.06.001.
G. Stiny and J. Gips. "Shape Grammars and the Generative Specification of Painting and Sculpture," in IFIP Congress, 1971, pp. 1460-1465.
A. Lindenmayer. "Mathematical models for cellular interactions in development II. Simple and branching filaments with two-sided inputs," Journal of Theoretical Biology, vol. 18, no. 3, 1968, pp. 300-315, doi: 10.1016/0022-5193(68)90080-5.
J. Von Neumann. "The General and Logical Theory of Automata," in Jeffress, L.A., Ed., Cerebral Mechanisms in Behavior: The Hixon Symposium, John Wiley & Sons, New York, 1951, pp. 1-41.
Holland, J. H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence, MIT press, 1992.
S. Wolfram and A. Mallinckrodt. "Cellular Automata And Complexity," Computers in Physics 9, 1995, pp. 55. doi: 10.1063/1.4823369.
J. L. Deneubourg. "Application de l’ordre par fluctuations á la descriptions de certaines étapes de la construction du nid chez les termites," Insect. Soc. 24, 1997, pp. 117-139.
W. Rawat, Z. Wang. "Deep convolutional neural networks for image classification: A comprehensive review", Neural computation, vol. 29, no. 9, pp. 2352-2449, 2017.
N. Van Noord, E. Postma. "Learning scale-variant and scale-invariant features for deep image classification," Pattern Recognition, vol. 61, pp. 583-592, 2017.
A. Krizhevsky, I. Sutskever, G. E. Hinton. "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, v. 25, pp. 1097-1105, 2012.
M. J. Harris and A. Lastra. "Real-time cloud rendering for games," in Proceedings of Game Developers Conference, 2002, pp. 21–29.
D. S. Ebert. Texturing & modeling: a procedural approach, Morgan Kaufmann, 2003.
P. Man. "Generating and real-time rendering of clouds," in Central European seminar on computer graphics, Citeseer, 2006, pp. 1–9.
Y. Dobashi,W. Iwasaki, A. Ono, T. Yamamoto, Y. Yue, and T. Nishita. "An inverse problem approach for automatically adjusting the parameters for rendering clouds using photographs," ACM Trans. Graph., 2012, pp. 145.
Y. Dobashi, K. Kaneda, H. Yamashita, T. Okita, and T. Nishita. "A simple, efficient method for realistic animation of clouds," in Proceedings of the 27th annual conference on Computer graphics and interactive techniques, ACM Press/Addison-Wesley Publishing Co., 2000, pp. 19–28.
Y. Dobashi, K. Kusumoto, T. Nishita, and T. Yamamoto. "Feedback control of cumuliform cloud formation based on computational fluid dynamics," ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008), vol. 27, no. 3, 2008.
J. Xu, C. Yang, J. Zhao, and L. Wu. "Fast modeling of realistic clouds," in Computer Network and Multimedia Technology, CNMT 2009. International Symposium on, IEEE, 2009, pp. 1–4.
Cloud image classification Dataset, Kaggle, Oct. 2021 [Online]. Available: https://www.kaggle.com/nakendraprasathk/cloud-image-classification-dataset
Public Domain Pictures, Oct. 2021 [Online]. Available: https://www.publicdomainpictures.net/
Cumulus, Wikipedia a Free Encyclopedia, Oct. 2021 [Online]. Available: https://en.wikipedia.org/wiki/Cumulus_cloud
Generative Design Applied to Cloud Modeling, Project Perfect Game, Oct. 2021 [Online]. Available: https://cloudsbgames2021.carloseduardomuniz.com/
