# Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images

arXiv: https://arxiv.org/abs/2605.07978 · HTML: https://mlsanity.com/paper/2605.07978/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 46 of its 58 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 46)

- [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)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos](https://mlsanity.com/paper/2412.09401/) (2024)
- [Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image](https://mlsanity.com/paper/2204.04752/) (2022)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion](https://mlsanity.com/paper/2012.02177/) (2020)
- [SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite](https://mlsanity.com/paper/2204.10704/) (2022)
- [Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator](https://mlsanity.com/paper/2308.16906/) (2023)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation](https://mlsanity.com/paper/2211.14651/) (2022)
- [Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching](https://mlsanity.com/paper/2203.14148/) (2022)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)

## Abstract (arXiv)

Cross-view localization classically asks: where does this ground image lie on the satellite tile? Existing methods are typically limited to 3-DoF estimates -- an (x,y) position and a yaw angle -- because nadir satellite imagery provides no direct cues for roll, pitch, or altitude, forcing a reliance on planar-motion and zero-tilt assumptions. These assumptions break on real terrain with slopes, ramps, and tilted camera mounts. To overcome this, we introduce a single UAV image as an intermediate viewpoint: it reveals the 3D structure invisible from nadir, supplies the cues for roll, pitch, and altitude that the satellite alone cannot provide, and needs only spatial overlap with the ground camera -- no known relative pose is required. Building on this insight, we propose **Cross3R**, a flexible feed-forward model that ingests a satellite tile together with a UAV image, a ground image, or both, and, in a single forward pass, recovers a cross-view 3D point cloud, the 6-DoF poses of every input camera, and the on-tile (x,y) position and yaw of each perspective camera. For training and evaluation, we also construct **CrossGeo**, a 278K-image tri-view dataset spanning 85 scenes across every continent except Antarctica. On CrossGeo, Cross3R consistently outperforms feed-forward 3D baselines in point-cloud reconstruction, 6-DoF camera-pose estimation, and cross-view localization. On KITTI, it outperforms dedicated cross-view methods trained on KITTI on most metrics, despite having no KITTI training itself.