Diffusion Transformers for Roof Graph Synthesis and Reconstruction

2026-08-26

AI Summary

本文提出RoofDiT，一种基于扩散变换器的框架，用于2D屋顶图生成和重建，通过学习几何与连接性的条件生成先验来提高屋顶结构合成质量。

Abstract

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.

Problem

• roof graph
• synthesis
• reconstruction
• geometric rules
• generative prior

Innovation

• diffusion transformer
• geometry-aware attention
• alignment regularizer
• conditional generative prior