GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame

2026-08-30

AI Summary

本文提出GeoRay方法，解决卫星摄影测量中绝对地理框架下的密集表面高度重建问题，通过轻量级射线一致适配器和显式基准机制实现。

Abstract

Feed-forward 3D foundation models reconstruct perspective scenes in one pass. Satellite photogrammetry needs a different product, one that domain adaptation alone does not deliver: dense surface height in an absolute geodetic frame under non-central rational polynomial cameras (RPCs). Perspective-pretrained features are not reliably observable along RPC height rays, absolute elevation carries a low-order height--datum gauge exchangeable with sensor bias to first order, and monocular and multi-view cues fail in different regions. \method{} treats all three. Lightweight ray-consistent adapters make a frozen backbone matchable along native RPC rays. An explicit datum mechanism separates relief from absolute level and is equivariant to the vertical origin by construction, so one trained model serves zero-, one-, and sparse-control inference. Calibrated inverse-variance fusion combines the two relief streams. \bench{}, our absolute-frame benchmark of eighteen systems across in-domain, cross-dataset, and cross-city tiers, scores absolute placement without registration or test-reference leakage. On 26 held-out US3D tiles, \method{} attains $2.99$\,m absolute MAE at $91.9\%$ coverage, improves completeness-aware accuracy by $46.4$ points over the strongest compliant feed-forward baseline, remains the most accurate such system under both transfer shifts, and runs in $24$\,s model-forward time per tile. Code and models will be released at https://github.com/HIT-SIRS/GeoRay

Problem

• satellite photogrammetry
• absolute geodetic frame
• non-central rational polynomial cameras (RPCs)
• datum gauge
• multi-view cues

Innovation

• Gauge-Aware
• Feed-Forward 3D Reconstruction
• Geodetic Frame
• Ray-Consistent Adapters
• Datum Mechanism