RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion

Abstract

Accurate completion and denoising of roof height maps are crucial to reconstructing high-quality 3D buildings. Repairing sparse points can enhance low-cost sensor use and reduce UAV flight overlap. is a new end-to-end self-supervised diffusion technique for robustly completing, in particular difficult, roof height maps. leverages widely-available curated footprints and can so handle up to 99% point sparsity and 80% roof area occlusion (regional incompleteness). A variant, , simultaneously predicts building footprints and heights. Both quantitatively outperform state-of-the-art unguided depth completion and representative inpainting methods for Digital Elevation Models (DEM), on both a roof-specific benchmark and the BuildingNet dataset. Qualitative assessments show the effectiveness of for datasets with real-world scans including AHN3, Dales3D, and USGS 3DEP LiDAR. Tested with the leading City3D algorithm, preprocessing height maps with noticeably improves 3D building reconstruction. is complemented by a new dataset of 13k complex roof geometries, focusing on long-tail issues in remote sensing; a novel simulation of tree occlusion; and a wide variety of large-area roof cut-outs for data augmentation and benchmarking. Code and dataset1 : github.com/kylelo/RoofDiffusion 1 Created and released by the University of Florida