# EO-VGGT: Orbital Ray-Conditioned 3D Foundation Models for Satellite Multi-View Reconstruction

arXiv: https://arxiv.org/abs/2607.00417 · HTML: https://mlsanity.com/paper/2607.00417/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [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)
- [Semantic Stereo for Incidental Satellite Images](https://mlsanity.com/paper/1811.08739/) (2018)
- [Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs](https://mlsanity.com/paper/2303.14672/) (2023)
- [Leveraging Vision Reconstruction Pipelines for Satellite Imagery](https://mlsanity.com/paper/1910.02989/) (2019)
- [Gaussian Splatting for Efficient Satellite Image Photogrammetry](https://mlsanity.com/paper/2412.13047/) (2024)
- [Rational Polynomial Camera Model Warping for Deep Learning Based Satellite Multi-View Stereo Matching](https://mlsanity.com/paper/2109.11121/) (2021)
- [SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite Imagery](https://mlsanity.com/paper/2403.18711/) (2024)
- [SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images](https://mlsanity.com/paper/2508.09479/) (2025)
- [3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions](https://mlsanity.com/paper/2404.04823/) (2024)
- [ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images](https://mlsanity.com/paper/2106.08107/) (2021)
- [Seeing through Satellite Images at Street Views](https://mlsanity.com/paper/2505.17001/) (2025)
- [Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision](https://mlsanity.com/paper/2502.08352/) (2025)
- [An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks](https://mlsanity.com/paper/2507.14798/) (2025)
- [Comparative Analysis of Advanced Feature Matching Algorithms in Challenging High Spatial Resolution Optical Satellite Stereo Scenarios](https://mlsanity.com/paper/2405.06246/) (2024)
- [Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery](https://mlsanity.com/paper/2606.17564/) (2026)

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

- [GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame](https://mlsanity.com/paper/2608.29680/) (2026)

## Abstract (arXiv)

In the era of satellite constellations, multi-view optical satellite imagery is pivotal for Earth Observation (EO) and high-quality Digital Surface Model (DSM) reconstruction. Although feed-forward 3D foundation models have transformed computer vision, their deployment in satellite remote sensing is inherently constrained by the structural discrepancy between implicit perspective assumptions and explicit orbital pushbroom geometry. This geometric incongruity is further compounded by pronounced view-set heterogeneity. We present EO-VGGT, a framework that adapts a frozen perspective-driven model to orbital observations via explicit physical geometry embedding.First, the Geometry-Correlation Constrained Selection (GCCS) strategy prunes sub-optimal observations by balancing geometric diversity and radiometric consistency to optimize the input sequence. Second, a Sensor-Ray Encoder (SRE) parameterizes pixel-level pushbroom lines of sight derived from the Rational Function Model (RFM) into high-dimensional space-geometric tokens, reconciling the mathematical discrepancy between central projection and orbital kinematics. Third, a lightweight Ray-Pointing-Aware Adapter (RPAA) employs gated residual blocks to integrate these tokens directly into the frozen transformer backbone. Our findings underscore that integrating explicit physical geometry with optimized view selection is essential for robust feed-forward satellite 3D reconstruction.