SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery

• URL: http://arxiv.org/abs/2606.28581v1
• Date: Fri, 26 Jun 2026 20:14:19 GMT
• Title: SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery
• Abstract summary: We present SatSplat, the first framework to adapt 2D Gaussian Splatting (2DGS) to satellite photogrammetry, with online camera adjustment.<n>SatSplat achieves strong geometric accuracy while significantly outperforming prior 3DGS-based baselines.<n>Our approach enables large-scale digital surface modeling with practical computational efficiency.
• Score: 9.341363879764828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-resolution satellite imagery demands 3D reconstruction methods that deliver both speed and geometric accuracy. Recent adaptations of 3D Gaussian Splatting (3DGS) to satellite imagery demonstrate strong efficiency, but reconstruction quality often degrades under diverse illumination across multi-date, high-altitude acquisitions (with small intersection angles), limiting applicability to remote sensing and vision tasks. We present SatSplat, the first framework to adapt 2D Gaussian Splatting (2DGS) to satellite photogrammetry, with online camera adjustment. We approximate satellite cameras with an affine model and learn a minimal delta parameterization for in-splat camera refinement from dense observations. The formulation is implemented with a 2DGS scene representation. To handle time-varying shadows and illumination changes, we integrate geometric shadow mapping and per-camera color correction during training. Across the evaluated DFC2019 and IARPA2016 benchmark sites, SatSplat achieves strong geometric accuracy while significantly outperforming prior 3DGS-based baselines. On our processed DFC2019 benchmark, SatSplat reduces mean absolute error by 11.93% and peak video memory by 31% relative to the previous state of the art. Our approach enables large-scale digital surface modeling with practical computational efficiency. The project page is available at https://gdaosu.github.io/satsplat/.

Related papers

• ACEsplat: Accelerated 3D Gaussian Scene Regression via RGB and Poses Only [4.0553083073432]
  We present ACEsplat, a fast per-scene optimization framework that reconstructs 3D Gaussian representations from RGB images and camera poses only.<n>On static-view rendering, ACEsplat achieves 29.11 dB PSNR on Wayspots with real-time SLAM poses and 33.20 dB on Cambridge Landmarks with SfM-refined poses.
  arXiv  Detail & Related papers  (2026-06-20T15:16:24Z)
• ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery [7.33738775121714]
  We propose ShadowGS, a novel framework based on 3DGS.<n>It precisely model geometrically consistent shadows while maintaining efficient rendering.<n>It exhibits robust performance across various settings, including RGB, pansharpened, and sparse-view satellite inputs.
  arXiv  Detail & Related papers  (2026-01-04T06:33:59Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images [14.193740794354607]
  Three-dimensional scene reconstruction from sparse-viewizable satellite images is a long-standing and challenging task.<n>We propose SkySplat, a novel framework that integrates the RPC model into the generalizable 3DGS pipeline.<n>Compared to per-scene optimization methods, SkySplat achieves an 86 times speedup over EOGS with higher accuracy.
  arXiv  Detail & Related papers  (2025-08-13T04:17:51Z)
• GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction [51.99776072246151]
  We propose a novel reconstruction method called GS-2DGS for reflective objects based on 2D Gaussian Splatting (2DGS)<n> Experimental results on synthetic and real datasets demonstrate that our method significantly outperforms Gaussian-based techniques in terms of reconstruction and relighting.
  arXiv  Detail & Related papers  (2025-06-16T05:40:16Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction.<n>We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence.<n>Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion [20.464224937528222]
  Differentiable 3D-Gaussian splatting (GS) is emerging as a prominent technique in computer vision and graphics for reconstructing 3D scenes. GS suffers from a well-known'missing cone' problem, which results in poor reconstruction along the depth axis. We propose fusion algorithms that simultaneously utilize RGB camera data and sonar data.
  arXiv  Detail & Related papers  (2024-04-06T17:23:43Z)
• 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)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.<n>We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images.<n>We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)

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.