Evaluating Alternatives to SFM Point Cloud Initialization for Gaussian Splatting

TL;DR

This paper explores alternative initialization methods for Gaussian Splatting in 3D scene reconstruction, showing that with improved strategies and neural radiance field distillation, SFM dependency can be reduced or eliminated.

Contribution

The study introduces novel initialization strategies and demonstrates how NeRF-based structure distillation can replace SFM point clouds in Gaussian Splatting.

Findings

Random initialization can outperform traditional methods with proper design

NeRF-based structure distillation achieves comparable or better results than SFM initialization

Proposed methods reduce reliance on high-quality SFM point clouds

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. Source code is available at https://theialab.github.io/nerf-3dgs .