3D Gaussian Splatting has emerged as an alternative 3D representation of Neural Radiance Fields (NeRFs), benefiting from its high-quality rendering results and real-time rendering speed. Considering the 3D Gaussian representation remains unparsed, it is necessary first to execute object segmentation within this domain. Subsequently, scene editing and collision detection can be performed, proving vital to a multitude of applications, such as virtual reality (VR), augmented reality (AR), game/movie production, etc. In this paper, we propose a novel approach to achieve object segmentation in 3D Gaussian via an interactive procedure without any training process and learned parameters. We refer to the proposed method as SA-GS, for Segment Anything in 3D Gaussians. Given a set of clicked points in a single input view, SA-GS can generalize SAM to achieve 3D consistent segmentation via the proposed multi-view mask generation and view-wise label assignment methods. We also propose a cross-view label-voting approach to assign labels from different views. In addition, in order to address the boundary roughness issue of segmented objects resulting from the non-negligible spatial sizes of 3D Gaussian located at the boundary, SA-GS incorporates the simple but effective Gaussian Decomposition scheme. Extensive experiments demonstrate that SA-GS achieves high-quality 3D segmentation results, which can also be easily applied for scene editing and collision detection tasks. Codes will be released soon.

翻译：3D高斯泼溅（3D Gaussian Splatting）作为一种替代神经辐射场（NeRF）的三维表示，凭借其高质量渲染结果与实时渲染速度的优势而崭露头角。考虑到3D高斯表示尚未被解析，首先需要在该领域内执行物体分割。随后可进行场景编辑与碰撞检测操作，这对虚拟现实（VR）、增强现实（AR）、游戏/电影制作等众多应用至关重要。本文提出了一种新颖方法，通过无需训练过程与学习参数的交互式流程，实现3D高斯中的物体分割。我们将所提方法称为SA-GS（Segment Anything in 3D Gaussians）。给定单个输入视图中的一组点击点，SA-GS可通过所提出的多视图掩码生成与视图级标签分配方法，泛化SAM实现3D一致分割。我们还提出了一种跨视图标签投票方法，用于分配来自不同视图的标签。此外，为解决因位于边界处的3D高斯空间尺寸不可忽略导致的被分割物体边界粗糙问题，SA-GS融入了简单但有效的高斯分解（Gaussian Decomposition）方案。大量实验表明，SA-GS可实现高质量的3D分割结果，并能轻松应用于场景编辑与碰撞检测任务。代码即将开源。