发表机构
Thales; Centre National d’Études Spatiales (CNES)（泰雷兹集团; 法国国家空间研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出利用预训练扩散模型，结合摄影测量DSM与Pléiades影像的多模态条件，精化卫星立体摄影测量生成的高程模型，显著降低密集城区高程误差。
AI 中文摘要
大规模数字表面模型（DSMs）可通过立体摄影测量从卫星图像中经济高效地生成。然而，由此产生的三维地图常受噪声、离群值和空洞的污染。另一方面，航空激光雷达（LiDAR）能以显著更高的成本提供高精度高程测量。在本工作中，我们研究了以摄影测量DSMs和Pléiades影像为条件的扩散模型，用于精化垂直配准后的DSMs。我们引入了一种改进的Stable Diffusion 3架构，采用精简的文本流和分块归一化策略，使得在LiDAR数据上能够稳定训练，并实现从自然图像到高程图的迁移。在法国城市的实验中，多模态条件显著提升了高程精度，在上下文城市中，密集城区均方根误差（RMSE）从6.00米降至3.45米；在保留城市波尔多中，从4.16米降至2.77米。
英文摘要
Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D maps are often contaminated by noise, outliers, and voids. On the other hand, aerial LiDAR provides high-accuracy elevation measurements at a substantially higher cost. In this work, we study diffusion models conditioned both on photogrammetric DSMs and Pléiades imagery to refine vertically co-registered DSMs. We introduce a modified Stable Diffusion 3 architecture with a pruned text stream and a patch-wise normalization strategy, enabling stable training on LiDAR data and transfer from natural images to elevation maps. Experiments in French cities demonstrate that multimodal conditioning improves elevation accuracy, reducing Dense Urban RMSE from 6.00 to 3.45 m in the in-context cities and from 4.16 to 2.77 m in the held-out city of Bordeaux.
Journal refRemote Sensing 18(19), 3303 (2026)
