Shape inference and grammar induction for example-based procedural generation

Authors: Gillis Hermans, Thomas Winters, Luc De Raedt
Publication Date: 2021-09-15
Publication Venue: Proceedings of the Twelfth International Conference on Computational Creativity
Abstract: Designers increasingly rely on procedural generation for automatic generation of content in various industries. These techniques require extensive knowledge of the desired content, and about how to actually implement such procedural methods. Algorithms for learning interpretable generative models from example content could alleviate both difficulties. We propose SIGI, a novel method for inferring shapes and inducing a shape grammar from grid-based 3D building examples. This interpretable grammar is well-suited for co-creative design. Applied to Minecraft buildings, we show how the shape grammar can be used to automatically generate new buildings in a similar style.

Citation

APA

Hermans, G., Winters, T., & De Raedt, L. (2021). Shape inference and grammar induction for example-based procedural generation. Proceedings of the Twelfth International Conference on Computational Creativity, 342–349.

Harvard

Hermans, G., Winters, T. and De Raedt, L. (2021) “Shape inference and grammar induction for example-based procedural generation,” in Proceedings of the Twelfth International Conference on Computational Creativity. Association for Computational Creativity (ACC), pp. 342–349.

Vancouver

Hermans G, Winters T, De Raedt L. Shape inference and grammar induction for example-based procedural generation. In: Proceedings of the Twelfth International Conference on Computational Creativity. Association for Computational Creativity (ACC); 2021. p. 342–9.

BibTeX

@inproceedings{hermans2021shapegrammar,
    author = {Hermans, Gillis and Winters, Thomas and De Raedt, Luc},
    booktitle = {Proceedings of the Twelfth International Conference on Computational Creativity},
    organization = {Mexico City, Mexico (Virtual)},
    pages = {342--349},
    publisher = {Association for Computational Creativity (ACC)},
    title = {Shape inference and grammar induction for example-based procedural generation},
    year = {2021},
    abstract = {Designers increasingly rely on procedural generation for automatic generation of content in various industries. These techniques require extensive knowledge of the desired content, and about how to actually implement such procedural methods. Algorithms for learning interpretable generative models from example content could alleviate both difficulties. We propose SIGI, a novel method for inferring shapes and inducing a shape grammar from grid-based 3D building examples. This interpretable grammar is well-suited for co-creative design. Applied to Minecraft buildings, we show how the shape grammar can be used to automatically generate new buildings in a similar style.},
    isbn = {978-989-54160-3-5},
    conference = {International Conference on Computational Creativity},
}

Back to all publications