The Role and Relationship of Initialization and Densification in 3D Gaussian Splatting
This work addresses a bottleneck in 3D reconstruction for computer vision researchers, but it is incremental as it focuses on benchmarking and analysis rather than introducing a new method.
The paper systematically studies the relationship between initialization and densification in 3D Gaussian Splatting, finding that current densification methods often fail to significantly improve over sparse SfM-based initialization, even with dense initializations like laser scans or stereo point clouds.
3D Gaussian Splatting (3DGS) has become the method of choice for photo-realistic 3D reconstruction of scenes, due to being able to efficiently and accurately recover the scene appearance and geometry from images. 3DGS represents the scene through a set of 3D Gaussians, parameterized by their position, spatial extent, and view-dependent color. Starting from an initial point cloud, 3DGS refines the Gaussians' parameters as to reconstruct a set of training images as accurately as possible. Typically, a sparse Structure-from-Motion point cloud is used as initialization. In order to obtain dense Gaussian clouds, 3DGS methods thus rely on a densification stage. In this paper, we systematically study the relation between densification and initialization. Proposing a new benchmark, we study combinations of different types of initializations (dense laser scans, dense (multi-view) stereo point clouds, dense monocular depth estimates, sparse SfM point clouds) and different densification schemes. We show that current densification approaches are not able to take full advantage of dense initialization as they are often unable to (significantly) improve over sparse SfM-based initialization. We will make our benchmark publicly available.