[Submitted on 19 Mar 2026 (v1), last revised 22 Jul 2026 (this version, v3)]

View PDF HTML (experimental)

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.

Submission history

From: Rong Fu [view email]
[v1] Thu, 19 Mar 2026 08:59:07 UTC (44,854 KB)
[v2] Sun, 5 Apr 2026 06:17:36 UTC (30,203 KB)
[v3] Wed, 22 Jul 2026 03:35:01 UTC (30,202 KB)