EffGS: Efficient and High-Fidelity Gaussian Splatting

2026-09-30

AI Summary

This study addresses the severe rendering quality degradation of 3D Gaussian Splatting in large-scale scenes caused by existing general acceleration methods. To this end, we propose EffGS, a framework that introduces a frequency-aware mechanism and learnable primitive scale modulation. By integrating importance scoring with a local density control strategy targeting only valid projection footprints, alongside compact box rasterization and an adaptive optimization algorithm, EffGS achieves both efficient training and high-fidelity rendering. Experimental results demonstrate that EffGS attains an optimal balance among rendering quality, computational overhead, and primitive count across diverse scene types, significantly outperforming existing baseline methods.

Abstract

3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality degradation when extended to more complex, large-scale scenes. To address this issue, we propose 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. EffGS combines frequency-aware guidance, localized density control, and adaptive primitive scale modulation. First, an importance scoring mechanism combines pixel-wise reconstruction errors with a difference-of-Gaussians mask scheduled over training to provide stage-dependent spatial guidance. Second, localized densification and pruning restricts density modifications to Gaussians with valid projected footprints in the sampled views. Third, learnable per-Gaussian scale modulation adjusts effective primitive extent during optimization while retaining the Compact Box rasterization rule. Extensive experiments on bounded and large-scale scene datasets demonstrate a favorable balance between reconstruction quality, training time, and primitive count. Component ablations and matched-primitive-budget comparisons further support the effectiveness of the framework.

Problem

• 3D Gaussian Splatting
• novel view synthesis
• large-scale scenes
• rendering quality degradation
• acceleration

Innovation

• 3D Gaussian Splatting
• Frequency-aware Guidance
• Localized Density Control
• Adaptive Scale Modulation
• Novel View Synthesis