Revising Densification in Gaussian Splatting

TL;DR

This paper improves 3D Gaussian Splatting by introducing a pixel-error driven density control mechanism, enhancing scene quality while maintaining efficiency.

Contribution

It proposes a novel, principled density control method based on pixel error, addressing ADC limitations and improving 3D scene quality.

Findings

Consistent quality improvements across benchmark scenes

Enhanced control over primitive density and scene complexity

Maintained efficiency with improved densification logic

Abstract

In this paper, we address the limitations of Adaptive Density Control (ADC) in 3D Gaussian Splatting (3DGS), a scene representation method achieving high-quality, photorealistic results for novel view synthesis. ADC has been introduced for automatic 3D point primitive management, controlling densification and pruning, however, with certain limitations in the densification logic. Our main contribution is a more principled, pixel-error driven formulation for density control in 3DGS, leveraging an auxiliary, per-pixel error function as the criterion for densification. We further introduce a mechanism to control the total number of primitives generated per scene and correct a bias in the current opacity handling strategy of ADC during cloning operations. Our approach leads to consistent quality improvements across a variety of benchmark scenes, without sacrificing the method's efficiency.