Building LEGO Using Deep Generative Models of Graphs
This work addresses the problem of generating physical object designs for hobbyists and designers, using LEGO as a platform for sequential assembly.
This paper explores the application of deep generative models to design physical objects, specifically LEGO structures. They developed a graph-structured neural network model that learns from human-built structures and generates visually compelling LEGO designs.
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.