SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

TL;DR

SwiftGS is a meta-learned system that enables rapid, accurate 3D surface reconstruction from satellite imagery in a single pass, reducing computational costs and handling diverse conditions.

Contribution

It introduces a novel episodic meta-learning approach with a hybrid Gaussian and SDF representation for immediate satellite surface recovery.

Findings

Achieves accurate DSM reconstruction with zero-shot inference.

Operates with significantly reduced computational cost.

Outperforms traditional per-scene optimization methods.

Abstract

Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster response, yet remains difficult due to illumination changes, sensor heterogeneity, and the cost of per-scene optimization. We introduce SwiftGS, a meta-learned system that reconstructs 3D surfaces in a single forward pass by predicting geometry-radiation-decoupled Gaussian primitives together with a lightweight SDF, replacing expensive per-scene fitting with episodic training that captures transferable priors. The model couples a differentiable physics graph for projection, illumination, and sensor response with spatial gating that blends sparse Gaussian detail and global SDF structure, and incorporates semantic-geometric fusion, conditional lightweight task heads, and multi-view supervision from a frozen geometric teacher under an uncertainty-aware multi-task loss. At inference, SwiftGS operates zero-shot with optional compact calibration and achieves accurate DSM reconstruction and view-consistent rendering at significantly reduced computational cost, with ablations highlighting the benefits of the hybrid representation, physics-aware rendering, and episodic meta-training.