EVSplitting: an efficient and visually consistent splitting algorithm for 3D Gaussian Splatting

Feng, Qi-Yuan, Cao, Geng-Chen, Chen, Hao-Xiang, Xu, Qun-Ce, Mu, Tai-Jiang, Martin, Ralph and Hu, Shi-Min ORCID: https://orcid.org/0000-0001-7507-6542 2024. EVSplitting: an efficient and visually consistent splitting algorithm for 3D Gaussian Splatting. Presented at: SIGGRAPH Asia 2024, Tokyo, Japan, 3 - 6 December. SA '24: SIGGRAPH Asia 2024 Conference Papers. ACM, pp. 1-11. 10.1145/3680528.3687592

PDF - Published Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (7MB)

Abstract

This paper presents EVSplitting, an efficient and visually consistent splitting algorithm for 3D Gaussian Splatting (3DGS). It is designed to make operating 3DGS as easy and effective as other 3D explicit representations, readily for industrial productions. The challenges of above target are: 1) The huge number and complex attributes of 3DGS make it tough to explicitly operate on 3DGS in a real-time and learning-free manner; 2) The visual effect of 3DGS is very difficult to maintain during explicit operations and 3) The anisotropism of Gaussian always leads to blurs and artifacts. As far as we know, no prior work can address these challenges well. In this work, we introduce a direct and efficient 3DGS splitting algorithm to solve them. Specifically, we formulate the 3DGS splitting as two minimization problems that aim to ensure visual consistency and reduce Gaussian overflow across boundary (splitting plane), respectively. Firstly, we impose conservations on the zero-, first- and second-order moments of the weighted Gaussian distribution to guarantee visual consistency. Secondly, we reduce the boundary overflow with a special constraint on the aforementioned conservations. With these conservations and constraints, we derive a closed-form solution for the 3DGS splitting problem. This yields an easy-to-implement, plug-and-play, efficient and fundamental tool, benefiting various downstream applications of 3DGS.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	ACM
ISBN:	979-8-4007-1131-2
Date of First Compliant Deposit:	17 December 2024
Last Modified:	17 Dec 2024 10:45
URI:	https://orca.cardiff.ac.uk/id/eprint/174775

Actions (repository staff only)

Edit Item