通过分频训练减少3D高斯点数量，提升渲染效率。
Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training
- 用拉普拉斯分解分阶段优化高低频结构
- 1K分辨率下提速1.73倍，4K下达1.74倍
- 可无缝集成现有方法，适合高分辨率场景
3D高斯点积训练中的主要瓶颈是高斯原语持续增长，导致优化成本上升、收敛变慢，尤其在高分辨率下更为明显。本文提出拉普拉斯频率层次结构，一种简单高效的3DGS方案，结合拉普拉斯图像分解与由粗到精的频率分阶段训练。在拟合低频结构后，将对应高斯场归档，使后续场只需优化高频残差，无需承载全部原始点数；推理时通过拉普拉斯式重建在图像域合成结果。该设计显著减少训练期间活跃高斯点数量，降低优化开销，加速训练过程。该方法即插即用，与已有3DGS加速技术正交，可直接与Taming-3DGS和FastGS等强基线结合，在保持良好重建质量的同时提升训练速度。在1K设置下分别实现1.73倍和1.21倍平均加速，在4K设置下达1.74倍和1.33倍，复杂场景及更高分辨率下优势更明显。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。