Paper · arXiv 2404.12547
Does Gaussian Splatting need SFM Initialization?
Yalda Foroutan, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
Various initialization strategies, including random initialization and structure distillation from NeRF models, can enhance Gaussian Splatting, achieving results comparable to or better than those obtained using SFM data.
Abstract
3D Gaussian Splatting has recently been embraced as a versatile and effective method for scene reconstruction and novel view synthesis, owing to its high-quality results and compatibility with hardware rasterization. Despite its advantages, Gaussian Splatting's reliance on high-quality point cloud initialization by Structure-from-Motion (SFM) algorithms is a significant limitation to be overcome. To this end, we investigate various initialization strategies for Gaussian Splatting and delve into how volumetric reconstructions from Neural Radiance Fields (NeRF) can be utilized to bypass the dependency on SFM data. Our findings demonstrate that random initialization can perform much better if carefully designed and that by employing a combination of improved initialization strategies and structure distillation from low-cost NeRF models, it is possible to achieve equivalent results, or at times even superior, to those obtained from SFM initialization.