Laplacian Frequency Hierarchies is proposed, a simple yet efficient 3DGS scheme that combines Laplacian image decomposition with coarse-to-fine, frequency-staged training, and reduces the number of active Gaussians during training, thereby lowering optimization overhead and accelerating training.
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.
EffGS, a more general acceleration framework that improves training and rendering efficiency while maintaining reconstruction quality comparable to or better than vanilla 3DGS across bounded and large-scale scenes, is proposed.
Chang-Bai Li, Shuo Yang, Yi-Chen Yang et al.· arXiv.org· 0 citations
The proposed framework provides a simple and effective path toward fast and inherently compact 3DGS training, and leverages a synergistic design: an L2 reconstruction loss to provide error-proportional gradients that stabilize optimization, and a novel Polarized Opacity Prior to actively manage the Gaussian population.
Zi-Ming Wang, Kai-Wen Duan, Ko-Wei Huang et al.· 0 citations
This paper proposes a method to address gradient vanishing with a piecewise truncated gradient formulation that improves the optimization stability and robustness to initializations and introduces a novel dataset for benchmarking dynamic Gaussian Splatting using synthetic 3D scenes.
Théo Morales, Nhat-Quynh Le-Pham, Robin Atkins et al.· 0 citations
4D Gaussian Splatting (4DGS) has emerged as a powerful dynamic scene representation, supporting real-time high quality rendering but suffers from prohibitive storage overhead. Existing methods typically attempt to solve this by treating compression as a per-scene optimization problem, limiting generalizability and appl...
Cheng-Zhen Wu, Ke-Le Liu, Si-Cheng Li et al.· 0 citations
InfoLoD introduces a Fisher-guided self-distillation scheme that uses the Fisher Information Matrix to select geometrically valid, information-rich pseudo viewpoints, enabling LoD training directly from a pre-trained 3DGS model without any original images.
Zhenyu Xia, Pengcheng Han, Lin Chen et al.· IEEE Transactions on Visuali...· 0 citations
3D Gaussian Splatting (3DGS) enables real-time novel view synthesis but produces millions of primitives through adaptive densification, leading to significant storage overhead. Learned-mask pruning methods such as LP-3DGS address this by assigning each Gaussian a learnable mask to identify and prune redundant primitive...
Donghun Ryu, Minhyeok Lee· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.