用神经辐射场指导3D高斯点云分割，解决边界模糊问题。
NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation
- 通过掩码方差分析定位边界模糊的高斯点，再用RBF插值构建连续特征场。
- 在NVOS等数据集上边界mIoU显著提升，达到当前最佳水平。
- 适合需要精细3D分割的场景，如机器人视觉和数字孪生。
3D高斯点云拼贴（3DGS）虽能高效实现逼真新视角合成，但其离散高斯表示导致物体边界常出现混叠和伪影，难以精准分割。本文提出NG-GS框架，显式解决边界离散化问题。首先通过掩码方差分析自动识别边界处模糊的高斯点；随后利用径向基函数（RBF）插值构建空间连续的特征场，并采用多分辨率哈希编码实现高效多尺度表达；最后通过联合优化策略，以对齐损失和空间连续性损失将3DGS与轻量级NeRF模块对齐，确保分割边界平滑一致。在NVOS、LERF-OVS和ScanNet等基准上的实验表明，该方法在边界mIoU指标上取得显著提升，达到当前最优性能。代码已开源：https://github.com/BJTU-KD3D/NG-GS。
原文摘要 · Abstract (English)
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, LERF-OVS, and ScanNet benchmarks demonstrate that our method achieves state-of-the-art performance, with significant gains in boundary mIoU. Code is available at https://github.com/BJTU-KD3D/NG-GS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。