3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. However, its rendering speed and model size still present bottlenecks, especially in resource-constrained settings. In this paper, we identify and address two key inefficiencies in 3D-GS to substantially improve rendering speed. These improvements also yield the ancillary benefits of reduced model size and training time. First, we optimize the rendering pipeline to precisely localize Gaussians in the scene, boosting rendering speed without altering visual fidelity. Second, we introduce a novel pruning technique and integrate it into the training pipeline, significantly reducing model size and training time while further raising rendering speed. Our Speedy-Splat approach combines these techniques to accelerate average rendering speed by a drastic across scenes from the Mip-NeRF 360, Tanks & Temples, and Deep Blending datasets.
View on arXiv@article{hanson2025_2412.00578,
title={ Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives },
author={ Alex Hanson and Allen Tu and Geng Lin and Vasu Singla and Matthias Zwicker and Tom Goldstein },
journal={arXiv preprint arXiv:2412.00578},
year={ 2025 }
}