Shape Inference and Grammar Induction for Example-based Procedural Generation

TL;DR

This paper introduces SIGI, a method for inferring shape grammars from 3D building examples to facilitate automatic, style-consistent content generation in design tasks like Minecraft building creation.

Contribution

The paper presents a novel approach for shape inference and grammar induction from 3D examples, enabling interpretable and co-creative procedural content generation.

Findings

Successfully inferred shape grammars from Minecraft buildings

Generated new buildings with similar style automatically

Enhanced co-creative design capabilities

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.