UAV-Assisted Scan-to-Simulation for Landslides Using Physics-Informed Gaussian Splatting
This work addresses the lack of visual realism in existing landslide simulation pipelines for hazard communication and public education, but the contribution is incremental as it combines known techniques (UAV, 3DGS, MPM) in a pipeline.
The paper proposes a UAV-based scan-to-simulation framework that uses 3D Gaussian Splatting to create photorealistic 3D scenes for physics-based landslide simulation, validated on a real landslide site in Hong Kong, achieving both realistic visual reconstruction and effective simulation.
Landslide monitoring and simulation play an important role in urban safety assessment and disaster prevention. Existing landslide simulation pipelines typically rely on digital elevation model and mesh-based representations, which are suitable for geometric analysis, but often lack visual realism. This limitation reduces their effectiveness in interactive applications, hazard communication, and public education. In this paper, we propose a UAV-based scan-to-simulation framework that bridges photorealistic scene capture and physics-based landslide simulation through 3DGS. Specifically, our pipeline includes four stages: (1) UAV-based acquisition of slope imagery, (2) reconstruction of a low-anisotropy 3DGS scene representation, (3) volumetric conversion of the target simulation region by filling the interior of the surface-based model, and (4) integration with the Material Point Method (MPM) for landslide simulation. We validate the proposed framework on a real landslide site in Hong Kong that experienced a severe landslide event. The results show that our method supports both realistic visual reconstruction and effective simulation.