Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting
This work addresses the challenge of deploying high-quality 3D reconstructions on devices like smartphones, representing an incremental improvement through a combination of existing strategies.
The paper tackles the problem of making Gaussian splatting (GS) for 3D reconstruction more efficient for resource-constrained devices by proposing Trick-GS, which achieves up to 2x faster training, 40x smaller disk size, and 2x faster rendering speed compared to vanilla GS while maintaining comparable accuracy.
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.