Publication | IEEE International Conference on Computer Vision 2021

Building-GAN

Graph-Conditioned Architectural Volumetric Design Generation

This paper extends the traditional 2D layout generation to 3D volumetric design.

Download publication

Abstract

Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation

Kai-Hung Chang, Chin-Yi Cheng, Jieliang Luo, Shingo Murata, Mehdi Nourbakhsh, Yoshito Tsuji

IEEE International Conference on Computer Vision (ICCV) 2021

Volumetric design is the first and critical step for professional building design, where architects not only depict the rough 3D geometry of the building but also specify the programs to form a 2D layout on each floor. Though 2D layout generation for a single story has been widely studied, there is no developed method for multi-story buildings. This paper focuses on volumetric design generation conditioned on an input program graph. Instead of outputting dense 3D voxels, we propose a new 3D representation named voxel graph that is both compact and expressive for building geometries. Our generator is a cross-modal graph neural network that uses a pointer mechanism to connect the input program graph and the output voxel graph, and the whole pipeline is trained using the adversarial framework. The generated designs are evaluated qualitatively by a user study and quantitatively using three metrics: quality, diversity, and connectivity accuracy. We show that our model generates realistic 3D volumetric designs and outperforms previous methods and baselines.

Related Resources

Article

2023

Exploring Additive Manufacturing with Autodesk Research

Exploring the rapidly evolving world of additive manufacturing and how…

Publication

2017

An Investigation of Generative Design for Heating

Energy consumption in buildings contribute to 41% of global carbon…

Publication

2011

Robotic Origamis: Self-Morphing Modular Robots

Programmable matter is a material that produces distinctive shapes or…

Publication

2019

Towards an Ontology for Generative Design of Mechanical Assemblies

In software-based generative design, a user specifies goals expressed…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us