3D Gaussian Splatting (3DGS) has emerged as a novel paradigm for 3D reconstruction from satellite imagery. However, in multi-temporal satellite images, prevalent shadows exhibit significant inconsistencies due to varying illumination conditions. To address this, we propose ShadowGS, a novel framework based on 3DGS. It leverages a physics-based rendering equation from remote sensing, combined with an efficient ray marching technique, to precisely model geometrically consistent shadows while maintaining efficient rendering. Additionally, it effectively disentangles different illumination components and apparent attributes in the scene. Furthermore, we introduce a shadow consistency constraint that significantly enhances the geometric accuracy of 3D reconstruction. We also incorporate a novel shadow map prior to improve performance with sparse-view inputs. Extensive experiments demonstrate that ShadowGS outperforms current state-of-the-art methods in shadow decoupling accuracy, 3D reconstruction precision, and novel view synthesis quality, with only a few minutes of training. ShadowGS exhibits robust performance across various settings, including RGB, pansharpened, and sparse-view satellite inputs.

翻译：三维高斯泼溅（3DGS）已成为卫星影像三维重建的新范式。然而，在多时相卫星影像中，由于光照条件的变化，普遍存在的阴影表现出显著的不一致性。为解决此问题，我们提出ShadowGS——一个基于3DGS的新型框架。该框架利用遥感领域的基于物理的渲染方程，结合高效的光线步进技术，在保持高效渲染的同时精确建模几何一致的阴影。此外，该方法能有效解耦场景中不同的光照分量与表观属性。进一步地，我们引入了一种阴影一致性约束，显著提升了三维重建的几何精度。我们还结合了一种新颖的阴影图先验，以提升稀疏视角输入下的性能。大量实验表明，ShadowGS在阴影解耦精度、三维重建准确性和新视角合成质量上均优于当前最先进方法，且仅需数分钟的训练时间。ShadowGS在多种设置下均表现出鲁棒的性能，包括RGB影像、全色锐化影像及稀疏视角卫星输入。