SOURCE-LINKED INTELLIGENCE

Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting Training

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global