Identifying Unnecessary 3D Gaussians using Clustering for Fast Rendering of 3D Gaussian Splatting

arXiv:2402.13827v1 Announce Type: new
Abstract: 3D Gaussian splatting (3D-GS) is a new rendering approach that outperforms the neural radiance field (NeRF) in terms of both speed and image quality. 3D-GS represents 3D scenes by utilizing millions of 3D Gaussians and projects these Gaussians onto the 2D image plane for rendering. However, during the rendering process, a substantial number of unnecessary 3D Gaussians exist for the current view direction, resulting in significant computation costs associated with their identification. In this paper, …

2d image 3d scenes abstract arxiv clustering cs.ar cs.cv image nerf neural radiance field projects quality rendering speed terms type