Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification

2026-04-30

AI Summary

This work addresses the challenge in conventional 3D Gaussian splatting methods, which often conflate geometric misalignment with frequency aliasing, leading to blurred high-frequency textures or excessive densification. To resolve this, the authors propose a structure-aware densification framework that integrates structure tensors with Laplacian scale-space analysis to perform multi-scale frequency characterization. This approach defines a per-Gaussian, per-axis frequency violation metric η, which guides anisotropic splitting decisions. By incorporating multi-view consistency constraints, the method enables efficient early-stage densification. Experimental results demonstrate that the proposed technique significantly accelerates convergence on standard benchmarks and achieves superior reconstruction quality in high-frequency regions.

Abstract

3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either over-blurred high-frequency textures or inefficient over-densification. We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. We introduce a multi-scale frequency analysis combining structure tensors with Laplacian scale space analysis to estimate the dominant frequency at each pixel, enabling robust supervision across varying texture scales. Based on this analysis, we define $η$, a per-Gaussian, per-axis frequency violation metric that indicates when a primitive may be under-resolving local texture details. Unlike methods that perform isotropic splitting (e.g., splitting each Gaussian into two smaller ones with uniform shape), our approach performs anisotropic splitting. For each axis with high $η$, we compute a split factor to better resolve the local frequency content. We further introduce a multiview consistency criterion that aggregates $η$ observations across multiple views. By performing densification early and faster, we skip the lengthy iterative densification phases required by baseline methods and achieve significantly faster convergence. Experiments on standard benchmarks demonstrate that our method also achieves superior reconstruction quality, particularly in high-frequency regions.

Problem

• 3D Gaussian Splatting
• density control
• frequency aliasing
• texture reconstruction
• convergence speed

Innovation

• structure-aware densification
• anisotropic splitting
• multi-scale frequency analysis
• 3D Gaussian Splatting
• multiview consistency