ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery
This work addresses shadow inconsistencies in satellite imagery reconstruction, which is crucial for remote sensing applications, but it is incremental as it builds upon the existing 3D Gaussian Splatting paradigm.
The paper tackled the problem of inconsistent shadows in 3D reconstruction from multi-temporal satellite imagery by proposing ShadowGS, a framework based on 3D Gaussian Splatting that models shadows using physics-based rendering and ray marching, resulting in improved shadow decoupling accuracy, 3D reconstruction precision, and novel view synthesis quality with only a few minutes of training.
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.