GaussianTrimmer: Online Trimming Boundaries for 3DGS Segmentation
This addresses boundary refinement for 3D Gaussian segmentation methods, which is an incremental improvement for 3D scene understanding applications.
The paper tackles the problem of jagged boundaries in 3D Gaussian segmentation caused by large Gaussians spanning foreground and background, proposing GaussianTrimmer as an online boundary trimming method that improves segmentation quality as a plug-and-play post-processing approach.
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.