Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training

2026-09-02

AI Summary

本文提出Laplacian Frequency Hierarchies方法，通过分阶段训练和图像域重构减少3D高斯点云训练中的优化成本，加速训练过程。

Abstract

A key bottleneck in 3D Gaussian Splatting training is the continual growth of Gaussian primitives, which increases optimization cost and slows convergence, especially at high resolutions. We propose Laplacian Frequency Hierarchies, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition with coarse-to-fine, frequency-staged training. After fitting lower-frequency structure, we archive the corresponding Gaussian field so that subsequent fields can optimize higher-frequency residuals without carrying the full primitive burden, and we compose the rendered components in the image domain via a Laplacian-style reconstruction at inference time. This design reduces the number of active Gaussians during training, thereby lowering optimization overhead and accelerating training. The proposed scheme is plug-and-play and orthogonal to prior 3DGS accelerations: it can be directly combined with strong backbones such as Taming-3DGS and FastGS to improve training speed with competitive reconstruction quality. It achieves average speedups of 1.73x and 1.21x at 1K setting, and 1.74x and 1.33x at 4K setting on Taming-3DGS and FastGS, with larger gains on more challenging scenes and increasingly pronounced benefits at higher resolutions.

Problem

• 3D Gaussian Splatting
• Gaussian primitives
• optimization cost
• convergence
• high resolutions

Innovation

• Laplacian Frequency Hierarchies
• coarse-to-fine training
• frequency-staged training
• Gaussian Splatting
• optimization efficiency