RoofDiffusion:基于扩散模型从严重损坏的点数据中构建屋顶
RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion
AI总结:
RoofDiffusion是一种新型端到端自监督扩散技术,利用建筑轮廓数据有效补全高度损坏的屋顶高度图,在多项数据集上优于现有方法,并显著提升3D建筑重建质量。
摘要:
屋顶高度图的精确补全与去噪对于重建高质量3D建筑至关重要。修复稀疏点能够促进低成本传感器的使用并降低无人机(UAV)飞行重叠率。RoofDiffusion是一种新型端到端自监督扩散技术,能够稳健地补全难度极高的屋顶高度图。该技术利用广泛可用的精选轮廓数据,从而能够处理高达99%的点稀疏度及80%的屋顶区域遮挡(区域不完整情况)。其变体No-FP RoofDiffusion可同时预测建筑轮廓与高度。在专用屋顶基准和BuildingNet数据集上,两者的定量表现均优于最先进的无引导深度补全方法及针对数字高程模型(DEM)的代表性图像修复方法。定性评估表明,RoofDiffusion在包含AHN3、Dales3D和USGS 3DEP LiDAR的真实世界扫描数据集中同样有效。结合领先的City3D算法测试,使用RoofDiffusion对高度图进行预处理可显著提升3D建筑重建效果。此外,本研究还提供了一个包含1.3万个复杂屋顶几何结构的新数据集,聚焦遥感领域的长尾问题;提出了一种新颖的树木遮挡模拟方法;并提供了多种大面积屋顶裁剪数据,用于数据增强与基准测试。
英文摘要:
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 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 RoofDiffusion for datasets with real-world scans including AHN3, Dales3D, and USGS 3DEP LiDAR. Tested with the leading City3D algorithm, preprocessing height maps with RoofDiffusion noticeably improves 3D building reconstruction. RoofDiffusion 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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。