NG-GS：神经辐射场引导的三维高斯泼溅分割
NG-GS: NeRF-guided 3D Gaussian Splatting Segmentation
针对 3DGS 离散高斯在物体边界处产生锯齿与伪影的问题，用掩码方差分析定位边界模糊高斯，并以 RBF 插值 + 多分辨率哈希编码构建空间连续特征场，再通过轻量 NeRF 模块的联合优化约束边界平滑；这套「连续特征场 + NeRF 引导」思路可直接迁移到 3DGS 的编辑、抠图与开放词表查询任务。
原文依据 automatically identifying ambiguous Gaussians at object boundaries using mask variance analysis
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维高斯泼溅（3DGS）的最新进展使高效、照片级真实感的新视角合成成为可能。然而，由于高斯表示的离散特性，在 3DGS 中精确分割物体仍然具有挑战性，这往往导致物体边界处出现锯齿与伪影。本文提出 NG-GS，一个用于 3DGS 中高质量物体分割的新框架，显式地处理边界离散化问题。我们的方法首先通过掩码方差分析自动识别位于物体边界处的模糊高斯。随后，我们采用径向基函数（RBF）插值构建空间连续的特征场，并通过多分辨率哈希编码加以增强，以实现高效的多尺度表示。一种联合优化策略借助对齐损失与空间连续性损失，使 3DGS 与一个轻量神经辐射场模块对齐，从而保证分割边界平滑且一致。在 NVOS 与 LERF-OVS 基准上的大量实验表明，本方法取得了最优性能，并在边界 mIoU 上获得显著提升。
英文原文摘要 1108 字符
Recent advances in 3D Gaussian Splatting (3DGS) have enabled highly efficient and photorealistic novel view synthesis. However, segmenting objects accurately in 3DGS remains challenging due to the discrete nature of Gaussian representations, which often leads to aliasing and artifacts at object boundaries. In this paper, we introduce NG-GS, a novel framework for high-quality object segmentation in 3DGS that explicitly addresses boundary discretization. Our approach begins by automatically identifying ambiguous Gaussians at object boundaries using mask variance analysis. We then apply radial basis function (RBF) interpolation to construct a spatially continuous feature field, enhanced by multi-resolution hash encoding for efficient multi-scale representation. A joint optimization strategy aligns 3DGS with a lightweight NeRF module through alignment and spatial continuity losses, ensuring smooth and consistent segmentation boundaries. Extensive experiments on NVOS and LERF-OVS benchmarks demonstrate that our method achieves state-of-the-art performance, with significant gains in boundary mIoU.