GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation

TL;DR

GaussianTrimmer is an efficient online post-processing method that refines 3D Gaussian segmentation boundaries by virtual camera-based trimming, significantly improving segmentation quality without retraining models.

Contribution

It introduces a novel plug-and-play boundary trimming technique for 3D Gaussian segmentation, addressing boundary jaggedness caused by large Gaussians.

Findings

Improves segmentation boundary quality in 3D Gaussian methods

Demonstrates effectiveness across multiple datasets

Enhances existing segmentation methods without retraining

Abstract

With the widespread application of 3D Gaussians in 3D scene representation, 3D scene segmentation methods based on 3D Gaussians have also gradually emerged. However, existing 3D Gaussian segmentation methods basically segment on the basis of Gaussian primitives. Due to the large variation range of the scale of 3D Gaussians, large-sized Gaussians that often span the foreground and background lead to jagged boundaries of segmented objects. To this end, we propose an online boundary trimming method, GaussianTrimmer, which is an efficient and plug-and-play post-processing method capable of trimming coarse boundaries for existing 3D Gaussian segmentation methods. Our method consists of two core steps: 1. Generating uniformly and well-covered virtual cameras; 2. Trimming Gaussian at the primitive level based on 2D segmentation results on virtual cameras. Extensive quantitative and qualitative experiments demonstrate that our method can improve the segmentation quality of existing 3D Gaussian segmentation methods as a plug-and-play method.