Shape Inference and Grammar Induction for Example-based Procedural Generation
This work addresses the need for easier procedural generation in design industries, though it is incremental as it builds on existing shape grammar and procedural generation concepts.
The authors tackled the problem of learning interpretable generative models from example content by proposing SIGI, a method for inferring shapes and inducing a shape grammar from grid-based 3D building examples, and demonstrated its application by automatically generating new buildings in a similar style for Minecraft.
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.