Saved in:
Bibliographic Details
Main Authors: Deng, Xiaobin, Diao, Changyu, Li, Min, Yu, Ruohan, Xu, Duanqing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12313
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.