CVAug 17, 2025

Improving Densification in 3D Gaussian Splatting for High-Fidelity Rendering

arXiv:2508.12313v18 citationsh-index: 2
Originality Incremental advance
AI Analysis

This work addresses a specific bottleneck in 3D Gaussian Splatting for high-fidelity rendering, offering incremental improvements to densification.

The paper tackled the problem of suboptimal reconstruction quality in 3D Gaussian Splatting's densification strategy by proposing improvements in when, how, and how to mitigate overfitting, resulting in state-of-the-art performance with fewer Gaussians and no additional overhead.

Although 3D Gaussian Splatting (3DGS) has achieved impressive performance in real-time rendering, its densification strategy often results in suboptimal reconstruction quality. In this work, we present a comprehensive improvement to the densification pipeline of 3DGS from three perspectives: when to densify, how to densify, and how to mitigate overfitting. Specifically, we propose an Edge-Aware Score to effectively select candidate Gaussians for splitting. We further introduce a Long-Axis Split strategy that reduces geometric distortions introduced by clone and split operations. To address overfitting, we design a set of techniques, including Recovery-Aware Pruning, Multi-step Update, and Growth Control. Our method enhances rendering fidelity without introducing additional training or inference overhead, achieving state-of-the-art performance with fewer Gaussians.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes