View-Dependent Uncertainty Estimation of 3D Gaussian Splatting
This work addresses uncertainty estimation for 3D scene reconstruction in computer vision, but it is incremental as it builds on the existing 3DGS framework.
The paper tackles the problem of uncertainty estimation in 3D Gaussian Splatting scenes, which is important for tasks like asset extraction and scene completion, by proposing a view-dependent per-gaussian feature modeled with spherical harmonics, achieving high accuracy and significantly faster performance than ensemble methods.
3D Gaussian Splatting (3DGS) has become increasingly popular in 3D scene reconstruction for its high visual accuracy. However, uncertainty estimation of 3DGS scenes remains underexplored and is crucial to downstream tasks such as asset extraction and scene completion. Since the appearance of 3D gaussians is view-dependent, the color of a gaussian can thus be certain from an angle and uncertain from another. We thus propose to model uncertainty in 3DGS as an additional view-dependent per-gaussian feature that can be modeled with spherical harmonics. This simple yet effective modeling is easily interpretable and can be integrated into the traditional 3DGS pipeline. It is also significantly faster than ensemble methods while maintaining high accuracy, as demonstrated in our experiments.