Abstract
Evolutionary algorithms (ES) have been used in the digital art scene since the 1970s. A popular application of genetic algorithms is to optimize the procedural placement of vector graphic primitives to resemble a given painting. In recent years, deep learning-based approaches have also been proposed to generate procedural drawings, which can be optimized using gradient descent. In this work, we revisit the use of evolutionary algorithms for computational creativity. We find that modern ES algorithms, when tasked with the placement of shapes, offer large improvements in both quality and efficiency compared to traditional genetic algorithms, and even comparable to gradient-based methods. We demonstrate that ES is also well suited at optimizing the placement of shapes to fit the CLIP model, and can produce diverse, distinct geometric abstractions that are aligned with human interpretation of language.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alteredqualia. Evolution of mona lisa in javascript and canvas (2008). https://alteredqualia.com/visualization/evolve/. Accessed 1 Dec 2021
Bertoni, F.: Minimalist architecture. Birkhäuser (2002)
Beyer, H.G.: The Theory of Evolution Strategies. Springer, Heidelberg (2001). https://doi.org/10.1007/978-3-662-04378-3
Beyer, H.G., Schwefel, H.P.: Evolution strategies-a comprehensive introduction. Nat. Comput. 1(1), 3–52 (2002)
Cason, K.: Genetic Draw (2016). https://github.com/kennycason/genetic_draw. Accessed 1 Dec 2021
Commons, W.: File:040 okertalsperre.jpg – wikimedia commons the free media repository (2020). https://commons.wikimedia.org/w/index.php?title=File:040_Okertalsperre.jpg&oldid=496749636. Accessed 1 Dec 2021
Crowson, K.: Introduction to vqgan+clip (2021). https://docs.google.com/document/d/1Lu7XPRKlNhBQjcKr8k8qRzUzbBW7kzxb5Vu72GMRn2E/edit. Accessed 1 Dec 2021
Dabrowski, M.: Geometric abstraction (2004). https://www.metmuseum.org/toah/hd/geab/hd_geab.htm. Accessed 1 Dec 2021
Fernando, C.: Royal academy summer exhibition 2021 submission (2021). https://www.chrisantha.co.uk/post/royal-academy-summer-exhibition-2021-submission. Accessed 1 Dec 2021
Fernando, C., Eslami, S., Alayrac, J.B., Mirowski, P., Banarse, D., Osindero, S.: Generative art using neural visual grammars and dual encoders. arXiv preprint arXiv:2105.00162 (2021)
Fogleman, M.: Primitive pictures (2016). https://github.com/fogleman/primitive. Accessed 1 Dec 2021
Frans, K., Soros, L., Witkowski, O.: Clipdraw: exploring text-to-drawing synthesis through language-image encoders. arXiv preprint arXiv:2106.14843 (2021)
Galatolo, F.A., Cimino, M.G., Vaglini, G.: Generating images from caption and vice versa via clip-guided generative latent space search. arXiv preprint arXiv:2102.01645 (2021)
Gonsalves, R.A.: Ganscapes: using AI to create new impressionist paintings (2021). https://towardsdatascience.com/ganscapes-using-ai-to-create-new-impressionist-paintings-d6af1cf94c56. Accessed 1 Dec 2021
Ha, D.: Evolving stable strategies. blog.otoro.net (2017). http://blog.otoro.net/2017/11/12/evolving-stable-strategies/. Accessed 1 Dec 2021
Ha, D., Eck, D.: A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477 (2017)
Harvey, I.: The microbial genetic algorithm. In: Kampis, G., Karsai, I., Szathmáry, E. (eds.) ECAL 2009. LNCS (LNAI), vol. 5778, pp. 126–133. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21314-4_16
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, F., Schoop, E., Ha, D., Canny, J.: Scones: towards conversational authoring of sketches. In: Proceedings of the 25th International Conference on Intelligent User Interfaces, pp. 313–323 (2020)
Huang, Z., Heng, W., Zhou, S.: Learning to paint with model-based deep reinforcement learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8709–8718 (2019)
Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904–4916. PMLR (2021)
Johansson, R.: Genetic programming: evolution of mona lisa (2008). https://rogerjohansson.blog/2008/12/07/genetic-programming-evolution-of-mona-lisa/. Accessed 1 Dec 2021
Kato, H., et al.: Differentiable rendering: a survey. arXiv preprint arXiv:2006.12057 (2020)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kolmogorov, A.: Three approaches to the quantitative definition of information. Probl. Inf. Trans. 1(1), 1–7 (1965)
Kuiper, K.: Modernism (2021). https://www.britannica.com/art/Modernism-art. Accessed 1 Dec 2021
Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. ACM Trans. Graph. 39(6), 1–14 (2020)
Li, T.M., Lukáč, M., Gharbi, M., Ragan-Kelley, J.: Differentiable vector graphics rasterization for editing and learning. ACM Trans. Graph. 39(6), 1–15 (2020)
Lindenmayer, A.: Mathematical models for cellular interactions in development i. filaments with one-sided inputs. J. Theoretic. Biol. 18(3), 280–299 (1968)
Liu, S., et al.: Paint transformer: feed forward neural painting with stroke prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6598–6607 (2021)
Lopes, R.G., Ha, D., Eck, D., Shlens, J.: A learned representation for scalable vector graphics. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7930–7939 (2019)
Malkevitchn, J.: Mathematics and art (2003). https://www.ams.org/publicoutreach/feature-column/fcarc-art1. Accessed 1 Dec 2021
Mellor, J.F., et al.: Unsupervised doodling and painting with improved spiral. arXiv preprint arXiv:1910.01007 (2019)
Modern, T.: Minimalism (2018). https://www.tate.org.uk/art/art-terms/m/minimalism. Accessed 1 Dec 2021
Paauw, M., van den Berg, D.: Paintings, polygons and plant propagation. In: Ekárt, A., Liapis, A., Castro Pena, M. (eds.) EvoMUSART 2019. LNCS, vol. 11453, pp. 84–97. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-16667-0_6
Paul, S.: Abstract expressionism (2004). https://www.metmuseum.org/toah/hd/abex/hd_abex.htm. Accessed 1 Dec 2021
Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)
Rewald, S.: Cubism. The Metropolitan Museum of Art (2014). https://www.metmuseum.org/toah/hd/cube/hd_cube.htm. Accessed 1 Dec 2021
Rose, B.: Abc art. Art Am. 53(5), 57–69 (1965)
Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint arXiv:1703.03864 (2017)
Schmidhuber, J.: Low-complexity art. Leonardo 30(2), 97–103 (1997)
Sehnke, F., Osendorfer, C., Rückstieß, T., Graves, A., Peters, J., Schmidhuber, J.: Parameter-exploring policy gradients. Neural Netw. 23(4), 551–559 (2010)
Shahrabi, S.: Procedural paintings with genetic evolution algorithm (2020). https://github.com/IRCSS/Procedural-painting. Accessed 1 Dec 2021
Sizigi Studios. Waifu labs (2019). https://waifulabs.com/. Accessed 1 Dec 2021
Tate. Process art (2021). https://www.tate.org.uk/art/art-terms/p/process-art. Accessed 1 Dec 2021
Toklu, N.E.: Pgpelib (2020). https://github.com/nnaisense/pgpelib. Accessed 1 Dec 2021
Toklu, N.E., Liskowski, P., Srivastava, R.K.: Clipup: a simple and powerful optimizer for distribution-based policy evolution. In: International Conference on Parallel Problem Solving from Nature, pp. 515–527. Springer (2020)
Verostko, R.: Algorithmic art (1994). http://www.verostko.com/algorithm.html. Accessed 1 Dec 2021
Wang, P.: Big sleep: a simple command line tool for text to image generation, using openai’s clip and a biggan (2021). https://github.com/lucidrains/big-sleep. Accessed 1 Dec 2021
White, T.: Shared visual abstractions. arXiv preprint arXiv:1912.04217 (2019)
Acknowledgements
We thank Toru Lin, Jerry Li, Yujin Tang, Yanghua Jin, Jesse Engel, Yifu Zhao for their comments, suggestions and kind helps.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tian, Y., Ha, D. (2022). Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts. In: Martins, T., Rodríguez-Fernández, N., Rebelo, S.M. (eds) Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2022. Lecture Notes in Computer Science, vol 13221. Springer, Cham. https://doi.org/10.1007/978-3-031-03789-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-03789-4_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-03788-7
Online ISBN: 978-3-031-03789-4
eBook Packages: Computer ScienceComputer Science (R0)