构建多高程视角数据集，推动跨空域3D场景建模与相机定位研究。
Sky2Ground: A Benchmark for Site Modeling under Varying Altitude
- 融合卫星、航拍与地面图像，构建多视角高程变化数据集
- 发现卫星图会降低定位性能，最大误差达18.1%提升
- 提出分阶段训练模型，显著提升多视角一致性
我们提出Sky2Ground，一个用于不同高度下相机定位、对应关系学习和重建的三视图数据集。该数据集结合结构化合成图像与真实野外图像，兼具可控的多视角几何关系与真实的场景噪声。51个站点包含数千张从卫星、航空到地面拍摄的图像，覆盖广泛高程范围和近乎正交的观测角度，支持从全局到局部的严格评估。我们对MASt3R、DUSt3R、Map Anything和VGGT等先进姿态估计模型进行了基准测试，发现使用卫星图像常导致性能下降，凸显高程跨度大时的挑战。同时考察重建方法，揭示稀疏几何重叠、视角差异及真实图像噪声带来的渲染质量下降问题。为此，我们提出SkyNet，采用分阶段训练策略增强卫星图像引入时的跨视图一致性。该模型在绝对性能上相较现有方法提升9.6%（RRA@5）和18.1%（RTA@5）。Sky2Ground与SkyNet共同构成大规模、多高程三维感知与可泛化相机定位的综合测试平台与基线。代码与模型将公开发布。
原文摘要 · Abstract (English)
We introduce Sky2Ground, a three-view dataset designed for varying altitude camera localization, correspondence learning, and reconstruction. The dataset combines structured synthetic imagery with real, in-the-wild images, providing both controlled multi-view geometry and realistic scene noise. Each of the 51 sites contains thousands of satellite, aerial, and ground images spanning wide altitude ranges and nearly orthogonal viewing angles, enabling rigorous evaluation across global-to-local contexts. We benchmark state of the art pose estimation models, including MASt3R, DUSt3R, Map Anything, and VGGT, and observe that the use of satellite imagery often degrades performance, highlighting the challenges under large altitude variations. We also examine reconstruction methods, highlighting the challenges introduced by sparse geometric overlap, varying perspectives, and the use of real imagery, which often introduces noise and reduces rendering quality. To address some of these challenges, we propose SkyNet, a model which enhances cross-view consistency when incorporating satellite imagery with a curriculum-based training strategy to progressively incorporate more satellite views. SkyNet significantly strengthens multi-view alignment and outperforms existing methods by 9.6% on RRA@5 and 18.1% on RTA@5 in terms of absolute performance. Sky2Ground and SkyNet together establish a comprehensive testbed and baseline for advancing large-scale, multi-altitude 3D perception and generalizable camera localization. Code and models will be released publicly for future research.Project page: https://sky2ground2026.github.io/sky2ground/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。