Building LEGO using Deep Generative Models of Graphs

NeurIPS 2020

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: Speakers: Rylee Thompson, Elahe Ghalebi K., Terrance DeVries, Graham W Taylor