SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

• URL: http://arxiv.org/abs/2603.18634v1
• Date: Thu, 19 Mar 2026 08:59:07 GMT
• Title: SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery
• Abstract summary: SwiftGS is a meta-learned system that reconstructs 3D surfaces in a single forward pass.<n>It replaces expensive per-scene fitting with episodic training that captures transferable priors.<n>At inference, SwiftGS operates zero-shot with optional compact calibration.
• Score: 6.657583814165929
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• GS$^{2}$CI: Robust Gaussian Splatting For Snapshot Compressive Imaging via Large Vision Model Priors [11.431101404661595]
  We propose a novel framework that reconstructs high-quality 3D scenes from a single Snapshot Compressive Imaging measurement.<n>Our method achieves the strongest overall performance, combining leading reconstruction quality and robustness to viewpoint variation with competitive computational efficiency.
  arXiv  Detail & Related papers  (2026-08-13T17:29:53Z)
• Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis [17.82023714307905]
  We propose a visual relocalization method that departs from classical correspondence-based pipelines.<n>Our key contribution is a geometry-aware training strategy that combines photometric and geometric losses.<n>We show that this joint optimization produces a 3DGS model that better fits the underlying scene geometry.
  arXiv  Detail & Related papers  (2026-07-24T09:46:07Z)
• R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting [59.29134814041703]
  Physical adversarial camouflage poses a severe security threat to autonomous driving systems.<n>Current methods fail to generalize across diverse geometric (e.g., viewing configurations) and radiometric variations.<n>We propose the Relightable Physical 3D Gaussian Splatting framework (R-PGA)
  arXiv  Detail & Related papers  (2026-03-27T04:38:04Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• Improved 3D Gaussian Splatting of Unknown Spacecraft Structure Using Space Environment Illumination Knowledge [7.2620484413601325]
  This work presents a novel pipeline to recover the 3D structure of an unknown target spacecraft from a sequence of images captured in space.<n>Learning 3DGS requires static scenes, an assumption in contrast to dynamic lighting conditions encountered in spaceborne imagery.<n>The trained 3DGS model can also be used for camera pose estimation through photometric optimization.
  arXiv  Detail & Related papers  (2025-12-30T05:35:35Z)
• Generalizable and Relightable Gaussian Splatting for Human Novel View Synthesis [49.67420486373202]
  GRGS is a generalizable and relightable 3D Gaussian framework for high-fidelity human novel view synthesis under diverse lighting conditions.<n>We introduce a Lighting-aware Geometry Refinement (LGR) module trained on synthetically relit data to predict accurate depth and surface normals.
  arXiv  Detail & Related papers  (2025-05-27T17:59:47Z)
• GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images [6.055104738156625]
  3D Gaussian Splatting (3DGS) has gained significant attention in the field of surface reconstruction.<n>We propose a method called GS-3I to address the challenge of robust surface reconstruction under inconsistent illumination.<n>We show that GS-3I can achieve robust and accurate surface reconstruction across complex illumination scenarios.
  arXiv  Detail & Related papers  (2025-03-16T03:08:54Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [86.87464903285208]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• GUS-IR: Gaussian Splatting with Unified Shading for Inverse Rendering [83.69136534797686]
  We present GUS-IR, a novel framework designed to address the inverse rendering problem for complicated scenes featuring rough and glossy surfaces. This paper starts by analyzing and comparing two prominent shading techniques popularly used for inverse rendering, forward shading and deferred shading. We propose a unified shading solution that combines the advantages of both techniques for better decomposition.
  arXiv  Detail & Related papers  (2024-11-12T01:51:05Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.