Search papers, labs, and topics across Lattice.
This paper introduces Laplacian Frequency Hierarchies, an innovative approach to 3D Gaussian Splatting (3DGS) training that addresses the optimization challenges posed by the growth of Gaussian primitives. By utilizing Laplacian image decomposition and a frequency-staged training strategy, the method allows for the efficient fitting of lower-frequency structures while optimizing higher-frequency residuals without the full primitive burden. The results demonstrate significant training speed improvements, achieving average speedups of 1.73x and 1.21x at 1K resolution, and 1.74x and 1.33x at 4K resolution, particularly benefiting more complex scenes and higher resolutions.
Speed up 3D Gaussian Splatting training by over 70% without sacrificing reconstruction quality through a novel frequency-staged approach.
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.
