Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting

TL;DR

Trick-GS introduces a combination of strategies to significantly improve the efficiency of Gaussian splatting for 3D reconstruction, enabling faster training, smaller models, and quicker rendering on resource-limited devices without sacrificing accuracy.

Contribution

It presents Trick-GS, a novel method that integrates progressive training, pruning, and acceleration techniques to enhance resource efficiency in Gaussian splatting.

Findings

Up to 2x faster training

40x smaller disk size

2x faster rendering speed

Abstract

Gaussian splatting (GS) for 3D reconstruction has become quite popular due to their fast training, inference speeds and high quality reconstruction. However, GS-based reconstructions generally consist of millions of Gaussians, which makes them hard to use on computationally constrained devices such as smartphones. In this paper, we first propose a principled analysis of advances in efficient GS methods. Then, we propose Trick-GS, which is a careful combination of several strategies including (1) progressive training with resolution, noise and Gaussian scales, (2) learning to prune and mask primitives and SH bands by their significance, and (3) accelerated GS training framework. Trick-GS takes a large step towards resource-constrained GS, where faster run-time, smaller and faster-convergence of models is of paramount concern. Our results on three datasets show that Trick-GS achieves up to 2x faster training, 40x smaller disk size and 2x faster rendering speed compared to vanilla GS, while having comparable accuracy.