RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion

arXiv:2404.09290v1 Announce Type: new
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. RoofDiffusion is a new end-to-end self-supervised diffusion technique for robustly completing, in particular difficult, roof height maps. RoofDiffusion leverages widely-available curated footprints and can so handle up to 99\% point sparsity and 80\% roof area occlusion (regional incompleteness). A variant, No-FP RoofDiffusion, simultaneously predicts building footprints and …

abstract arxiv buildings cost cs.cv data denoising diffusion eess.iv low maps quality reduce sensor type via