# Sky2Ground: A Benchmark for Site Modeling under Varying Altitude

arXiv: https://arxiv.org/abs/2603.13740 · HTML: https://mlsanity.com/paper/2603.13740/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 30 of 36)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering](https://mlsanity.com/paper/2112.05504/) (2021)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians](https://mlsanity.com/paper/2404.01133/) (2024)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [MatrixCity: A Large-scale City Dataset for City-scale Neural Rendering and Beyond](https://mlsanity.com/paper/2309.16553/) (2023)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [VR-NeRF: High-Fidelity Virtualized Walkable Spaces](https://mlsanity.com/paper/2311.02542/) (2023)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Sat-NeRF: Learning Multi-View Satellite Photogrammetry With Transient Objects and Shadow Modeling Using RPC Cameras](https://mlsanity.com/paper/2203.08896/) (2022)
- [CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes](https://mlsanity.com/paper/2411.00771/) (2024)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)
- [Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes](https://mlsanity.com/paper/2412.01745/) (2024)
- [CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction](https://mlsanity.com/paper/2503.23044/) (2025)
- [DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery](https://mlsanity.com/paper/2503.16964/) (2025)
- [Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty](https://mlsanity.com/paper/2408.15242/) (2024)
- [Learning Cross-view Visual Geo-localization without Ground Truth](https://mlsanity.com/paper/2403.12702/) (2024)
- [GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting](https://mlsanity.com/paper/2401.14032/) (2024)
- [Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials](https://mlsanity.com/paper/2307.03398/) (2023)
- [Cross-View Visual Geo-Localization for Outdoor Augmented Reality](https://mlsanity.com/paper/2303.15676/) (2023)
- [DRAGON: Drone and Ground Gaussian Splatting for 3D Building Reconstruction](https://mlsanity.com/paper/2407.01761/) (2024)
- [Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction](https://mlsanity.com/paper/2507.23006/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding](https://mlsanity.com/paper/2610.19102/) (2026)

## Abstract (arXiv)

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/