Refining Gaussian Splatting: A Volumetric Densification Approach

TL;DR

This paper introduces a novel volumetric densification method for 3D Gaussian Splatting that improves view synthesis quality by better managing point primitives through inertia-based density control.

Contribution

The paper proposes a new density control technique using inertia volumes and evaluates different point cloud initialization methods, enhancing 3DGS performance.

Findings

Outperforms vanilla 3DGS in reconstruction quality

Effective densification improves novel view synthesis

Demonstrates robustness across diverse scenes

Abstract

Achieving high-quality novel view synthesis in 3D Gaussian Splatting (3DGS) often depends on effective point primitive management. The underlying Adaptive Density Control (ADC) process addresses this issue by automating densification and pruning. Yet, the vanilla 3DGS densification strategy shows key shortcomings. To address this issue, in this paper we introduce a novel density control method, which exploits the volumes of inertia associated to each Gaussian function to guide the refinement process. Furthermore, we study the effect of both traditional Structure from Motion (SfM) and Deep Image Matching (DIM) methods for point cloud initialization. Extensive experimental evaluations on the Mip-NeRF 360 dataset demonstrate that our approach surpasses 3DGS in reconstruction quality, delivering encouraging performance across diverse scenes.