让卫星影像3D重建更准，专治光影不一致的阴影问题
ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery
- 基于物理光照模型与高效光线追踪，精准建模几何一致阴影
- 在多时相卫星图中实现更高精度的3D重建与新视角合成
- 适合处理稀疏视角、多光谱及全色锐化卫星数据
3D高斯点阵（3DGS）已成为从卫星影像进行3D重建的新范式。然而，在多时相卫星图像中，由于光照条件变化，阴影普遍存在显著不一致性。为此，我们提出ShadowGS，一种基于3DGS的新型框架。它结合遥感领域的物理渲染方程与高效的光线追踪技术，精确建模几何一致的阴影，同时保持高效渲染。该方法还能有效解耦场景中的不同光照成分与表观属性。此外，引入阴影一致性约束，显著提升3D重建的几何精度；并设计新的阴影图先验，提升稀疏视角输入下的性能。大量实验表明，ShadowGS在阴影解耦准确率、3D重建精度和新视角合成质量上均优于当前最先进方法，仅需数分钟训练时间。该方法在多种设置下表现稳健，包括RGB、全色锐化及稀疏视角卫星输入。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。