# GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation

Source: [GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation](<https://www.sota2.com/research/paper/69705db7e25ad2fa9d1ed40d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-22T05:00:21.476Z

Authors: Liwei Liao, Ronggang Wang

Published: 2026-01-19T03:03:54.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3DGS Segmentation on NVOS 1.0 (test)](<https://www.sota2.com/research/sota/3dgs-segmentation-on-nvos-1-0-test.md>): 3DGS Segmentation; NVOS 1.0 (test); mIoU: 92.5.

- [3DGS Segmentation on NVOS derived from LLFF (test)](<https://www.sota2.com/research/sota/3dgs-segmentation-on-nvos-derived-from-llff-test.md>): 3DGS Segmentation; NVOS derived from LLFF (test); Boundary Clarity: 0.695.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.12683>)

[PDF](<https://arxiv.org/pdf/2601.12683.pdf>)
