Building LEGO Using Deep Generative Models of Graphs

TL;DR

This paper introduces a graph-based generative model for designing LEGO structures, enabling the creation of visually appealing physical object designs by learning from human-built examples.

Contribution

It presents a novel graph neural network model specifically for generating LEGO assembly structures, bridging the gap between digital generative models and physical object design.

Findings

Model learns from human-designed LEGO structures

Produces visually compelling LEGO designs

Code is publicly available for replication

Abstract

Generative models are now used to create a variety of high-quality digital artifacts. Yet their use in designing physical objects has received far less attention. In this paper, we advocate for the construction toy, LEGO, as a platform for developing generative models of sequential assembly. We develop a generative model based on graph-structured neural networks that can learn from human-built structures and produce visually compelling designs. Our code is released at: https://github.com/uoguelph-mlrg/GenerativeLEGO.