# Diffusion Transformers for Roof Graph Synthesis and Reconstruction

arXiv: https://arxiv.org/abs/2608.25652 · HTML: https://mlsanity.com/paper/2608.25652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 10 of 10)

- [LayoutDM: Discrete Diffusion Model for Controllable Layout Generation](https://mlsanity.com/paper/2303.08137/) (2023)
- [HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising](https://mlsanity.com/paper/2211.13287/) (2022)
- [Topological Map Extraction from Overhead Images](https://mlsanity.com/paper/1812.01497/) (2018)
- [PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images](https://mlsanity.com/paper/2111.15491/) (2021)
- [HEAT: Holistic Edge Attention Transformer for Structured Reconstruction](https://mlsanity.com/paper/2111.15143/) (2021)
- [Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis](https://mlsanity.com/paper/2109.07683/) (2021)
- [Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses](https://mlsanity.com/paper/2012.09340/) (2020)
- [GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation](https://mlsanity.com/paper/2408.16258/) (2024)
- [Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation](https://mlsanity.com/paper/2401.07721/) (2024)
- [PolyRoof: Precision Roof Polygonization in Urban Residential Building with Graph Neural Networks](https://mlsanity.com/paper/2503.10913/) (2025)

## Abstract (arXiv)

We present RoofDiT, a generative framework for 2D roof graph synthesis and reconstruction. Roofs are compactly described as planar graphs of junctions and structural edges, but existing methods often rely on fixed geometric rules or direct reconstruction objectives. RoofDiT instead models roof structures directly as vertex-edge graphs and learns a conditional generative prior over their geometry and connectivity. Our framework follows a two-stage design: a diffusion transformer generates roof vertices, and an edge prediction module infers the corresponding graph topology. To improve geometric fidelity, RoofDiT combines relative geometry-aware attention with footprint and aerial-image conditioning, while using an alignment regularizer to encourage common horizontal, vertical, and diagonal roof patterns. The same model supports unconditional generation, footprint-conditioned synthesis, and image-guided reconstruction by changing the conditioning signal. Experiments show improved graph generation quality over a diffusion baseline, favorable performance against a straight-skeleton prior in the footprint-conditioned setting, and the highest edge F1 among compared methods for image-guided reconstruction.