# Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses

arXiv: https://arxiv.org/abs/2012.09340 · HTML: https://mlsanity.com/paper/2012.09340/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 8 of 8)

- [Graph Transformer GANs for Graph-Constrained House Generation](https://mlsanity.com/paper/2303.08225/) (2023)
- [Automated LoD-2 Model Reconstruction from Very-HighResolution Satellite-derived Digital Surface Model and Orthophoto](https://mlsanity.com/paper/2109.03876/) (2021)
- [Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation](https://mlsanity.com/paper/2401.07721/) (2024)
- [Computer-Aided Layout Generation for Building Design: A Review](https://mlsanity.com/paper/2504.09694/) (2025)
- [RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion](https://mlsanity.com/paper/2404.09290/) (2024)
- [3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction](https://mlsanity.com/paper/2307.05409/) (2023)
- [Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model](https://mlsanity.com/paper/2204.04139/) (2022)
- [Diffusion Transformers for Roof Graph Synthesis and Reconstruction](https://mlsanity.com/paper/2608.25652/) (2026)

## Abstract (arXiv)

This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships. Given the number of primitives, the generator produces a structured roof model as a graph, which consists of 1) primitive geometry as raster images at each node, encoding facet segmentation and angles; 2) inter-primitive colinear/coplanar relationships at each edge; and 3) primitive geometry in a vector format at each node, generated by a novel differentiable vectorizer while enforcing the relationships. The discriminator is trained to assess the primitive raster geometry, the primitive relationships, and the primitive vector geometry in a fully end-to-end architecture. Qualitative and quantitative evaluations demonstrate the effectiveness of our approach in generating diverse and realistic roof models over the competing methods with a novel metric proposed in this paper for the task of structured geometry generation. Code and data are available at https://github.com/yi-ming-qian/roofgan .