Terrain generation using Neural Transfer Style and Fractal Brownian Motion noise with constraints
Resumo
In the gaming industry, recent technological and economic growth has made it one of the most lucrative markets, driving demand for solutions that reduce costs and complexity in development. Procedural Content Generation (PCG) has emerged as a promising resource, particularly in terrain generation, which remains technically challenging. Existing approaches can be grouped into three categories: AI-based methods that provide realistic details, geometric techniques that enable scalability, and rule-based methods that enforce structural constraints. However, issues such as limited variety, quality, and customization remain. To address these challenges, we propose a system that integrates a Transfer Style Network with Fractal Brownian Motion (FBM) noise under user-defined constraints. This hybrid design generates terrains that are realistic, customizable, and semantically rich. Results show that our method preserves user constraints while producing diverse terrains similar to real-world samples, offering developers a robust and efficient tool for accelerating terrain creation and enhancing variability in game environments.Referências
Newzoo, “2023 newzoo free global games market report,” 2023, accessed on August 03, 2024. [Online]. Available: [link]
P. Rykała, “The growth of the gaming industry in the context of creative industries,” Biblioteka Regionalisty, vol. 20, pp. 124–136, 2020. [Online]. Available: 124-136 Rykala The growth of the gaming industry in the context of creative.pdf
N. Shaker, J. Togelius, and M. J. Nelson, Procedural content generation in games. Springer, 2016.
J. Liu, S. Snodgrass, A. Khalifa, S. Risi, G. N. Yannakakis, and J. Togelius, “Deep learning for procedural content generation,” Neural Computing and Applications, vol. 33, no. 1, pp. 19–37, 2021. [Online]. DOI: 10.1007/s00521-020-05383-8
T. Archer, “Procedurally generating terrain,” in 44th annual midwest instruction and computing symposium, Duluth, 2011, pp. 378–393.
T. Hyttinen, E. Mäkinen, and T. Poranen, “Terrain synthesis using noise by examples,” in Proceedings of the 21st International Academic Mindtrek Conference, ser. AcademicMindtrek ’17. New York, NY, USA: Association for Computing Machinery, 2017, p. 17–25. [Online]. DOI: 10.1145/3131085.3131099
T. Le, “Procedural terrain generation using perlin noise,” Graduate Project, California State Polytechnic University, Pomona, 2023, scholarWorks.
R. r. Spick and j. Walker, “Realistic and textured terrain generation using gans,” in Proceedings of the 16th ACM SIGGRAPH European Conference on Visual Media Production, 2019, pp. 1–10.
E. Guérin, J. Digne, E. Galin, and A. Peytavie, “Sparse representation of terrains for procedural modeling,” Computer Graphics Forum, vol. 35, no. 2, pp. 177–187, 2016. [Online]. Available: [link]
Y. Thorimbert, “Polynomial method for procedural terrain generation,” CoRR, vol. abs/1610.03525, 2016. [Online]. Available: [link]
R. Fischer, P. Dittmann, R. Weller, and G. Zachmann, “Autobiomes: procedural generation of multi-biome landscapes,” The Visual Computer, vol. 36, no. 10, pp. 2263–2272, 2020. [Online]. DOI: 10.1007/s00371-020-01920-7
C. Gasch, M. Chover, I. Remolar, and C. Rebollo, “Procedural modelling of terrains with constraints,” Multimedia Tools and Applications, vol. 79, no. 41, pp. 31 125–31 146, November 2020. [Online]. DOI: 10.1007/s11042-020-09476-3
P. Walsh and P. Gade, “Terrain generation using an interactive genetic algorithm,” in IEEE Congress on Evolutionary Computation, 2010, pp. 1–7.
M. Frade, F. F. de Vega, and C. Cotta, “Automatic evolution of programs for procedural generation of terrains for video games,” Soft Computing, vol. 16, no. 11, pp. 1893–1914, nov 2012. [Online]. DOI: 10.1007/s00500-012-0863-z
I. Antoniuk and P. Rokita, “Procedural generation of adjustable terrain for application in computer games using 2d maps,” in Pattern Recognition and Machine Intelligence, M. Kryszkiewicz, S. Bandyopadhyay, H. Rybinski, and S. K. Pal, Eds. Cham: Springer International Publishing, 2015, pp. 75–84.
N. M. Husnul Habib Yahya, H. Fabroyir, D. Herumurti, I. Kuswardayan, and S. Arifiani, “Dungeon’s room generation using cellular automata and poisson disk sampling in roguelike game,” in 2021 13th International Conference on Information, Communication Technology and System (ICTS), 2021, pp. 29–34.
E. Panagiotou and E. Charou, “Procedural 3d terrain generation using generative adversarial networks,” arXiv preprint arXiv:2010.06411, vol. 2, 2020.
A. Wulff-Jensen, N. N. Rant, T. N. Møller, and J. A. Billeskov, “Deep convolutional generative adversarial network for procedural 3d landscape generation based on dem,” in Interactivity, Game Creation, Design, Learning, and Innovation, A. L. Brooks, E. Brooks, and N. Vidakis, Eds. Cham: Springer International Publishing, 2018, pp. 85–94.
G. Voulgaris, I. Mademlis, and I. Pitas, “Procedural terrain generation using generative adversarial networks,” in 2021 29th European Signal Processing Conference (EUSIPCO), 2021, pp. 686–690.
Y.-L. Huang and X.-F. Yuan, “Styleterrain: A novel disentangled generative model for controllable high-quality procedural terrain generation,” Computers and Graphics, vol. 116, pp. 373–382, 2023. [Online]. Available: [link]
F. Merizzi, “Procedural terrain generation with style transfer,” 2024.
B. B. Mandelbrot and J. W. Van Ness, “Fractional brownian motions, fractional noises and applications,” SIAM Review, vol. 10, no. 4, pp. 422–437, 1968.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015, accessed on July 9, 2024. [Online]. Available: [link]
J. K. Haas, “A history of the unity game engine,” 2014.
P. Rykała, “The growth of the gaming industry in the context of creative industries,” Biblioteka Regionalisty, vol. 20, pp. 124–136, 2020. [Online]. Available: 124-136 Rykala The growth of the gaming industry in the context of creative.pdf
N. Shaker, J. Togelius, and M. J. Nelson, Procedural content generation in games. Springer, 2016.
J. Liu, S. Snodgrass, A. Khalifa, S. Risi, G. N. Yannakakis, and J. Togelius, “Deep learning for procedural content generation,” Neural Computing and Applications, vol. 33, no. 1, pp. 19–37, 2021. [Online]. DOI: 10.1007/s00521-020-05383-8
T. Archer, “Procedurally generating terrain,” in 44th annual midwest instruction and computing symposium, Duluth, 2011, pp. 378–393.
T. Hyttinen, E. Mäkinen, and T. Poranen, “Terrain synthesis using noise by examples,” in Proceedings of the 21st International Academic Mindtrek Conference, ser. AcademicMindtrek ’17. New York, NY, USA: Association for Computing Machinery, 2017, p. 17–25. [Online]. DOI: 10.1145/3131085.3131099
T. Le, “Procedural terrain generation using perlin noise,” Graduate Project, California State Polytechnic University, Pomona, 2023, scholarWorks.
R. r. Spick and j. Walker, “Realistic and textured terrain generation using gans,” in Proceedings of the 16th ACM SIGGRAPH European Conference on Visual Media Production, 2019, pp. 1–10.
E. Guérin, J. Digne, E. Galin, and A. Peytavie, “Sparse representation of terrains for procedural modeling,” Computer Graphics Forum, vol. 35, no. 2, pp. 177–187, 2016. [Online]. Available: [link]
Y. Thorimbert, “Polynomial method for procedural terrain generation,” CoRR, vol. abs/1610.03525, 2016. [Online]. Available: [link]
R. Fischer, P. Dittmann, R. Weller, and G. Zachmann, “Autobiomes: procedural generation of multi-biome landscapes,” The Visual Computer, vol. 36, no. 10, pp. 2263–2272, 2020. [Online]. DOI: 10.1007/s00371-020-01920-7
C. Gasch, M. Chover, I. Remolar, and C. Rebollo, “Procedural modelling of terrains with constraints,” Multimedia Tools and Applications, vol. 79, no. 41, pp. 31 125–31 146, November 2020. [Online]. DOI: 10.1007/s11042-020-09476-3
P. Walsh and P. Gade, “Terrain generation using an interactive genetic algorithm,” in IEEE Congress on Evolutionary Computation, 2010, pp. 1–7.
M. Frade, F. F. de Vega, and C. Cotta, “Automatic evolution of programs for procedural generation of terrains for video games,” Soft Computing, vol. 16, no. 11, pp. 1893–1914, nov 2012. [Online]. DOI: 10.1007/s00500-012-0863-z
I. Antoniuk and P. Rokita, “Procedural generation of adjustable terrain for application in computer games using 2d maps,” in Pattern Recognition and Machine Intelligence, M. Kryszkiewicz, S. Bandyopadhyay, H. Rybinski, and S. K. Pal, Eds. Cham: Springer International Publishing, 2015, pp. 75–84.
N. M. Husnul Habib Yahya, H. Fabroyir, D. Herumurti, I. Kuswardayan, and S. Arifiani, “Dungeon’s room generation using cellular automata and poisson disk sampling in roguelike game,” in 2021 13th International Conference on Information, Communication Technology and System (ICTS), 2021, pp. 29–34.
E. Panagiotou and E. Charou, “Procedural 3d terrain generation using generative adversarial networks,” arXiv preprint arXiv:2010.06411, vol. 2, 2020.
A. Wulff-Jensen, N. N. Rant, T. N. Møller, and J. A. Billeskov, “Deep convolutional generative adversarial network for procedural 3d landscape generation based on dem,” in Interactivity, Game Creation, Design, Learning, and Innovation, A. L. Brooks, E. Brooks, and N. Vidakis, Eds. Cham: Springer International Publishing, 2018, pp. 85–94.
G. Voulgaris, I. Mademlis, and I. Pitas, “Procedural terrain generation using generative adversarial networks,” in 2021 29th European Signal Processing Conference (EUSIPCO), 2021, pp. 686–690.
Y.-L. Huang and X.-F. Yuan, “Styleterrain: A novel disentangled generative model for controllable high-quality procedural terrain generation,” Computers and Graphics, vol. 116, pp. 373–382, 2023. [Online]. Available: [link]
F. Merizzi, “Procedural terrain generation with style transfer,” 2024.
B. B. Mandelbrot and J. W. Van Ness, “Fractional brownian motions, fractional noises and applications,” SIAM Review, vol. 10, no. 4, pp. 422–437, 1968.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015, accessed on July 9, 2024. [Online]. Available: [link]
J. K. Haas, “A history of the unity game engine,” 2014.
Publicado
30/09/2025
Como Citar
CUADROS, Rodrigo Andre Cayro; TOLEDO, Cláudio Fabiano Motta; PEREIRA, Leonardo Tortoro.
Terrain generation using Neural Transfer Style and Fractal Brownian Motion noise with constraints. In: WORKSHOP DE TRABALHOS EM ANDAMENTO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 38. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 228-233.
DOI: https://doi.org/10.5753/sibgrapi.est.2025.38302.
