We present a real-time tracking SLAM system that unifies efficient camera tracking with photorealistic feature-enriched mapping using 3D Gaussian Splatting (3DGS). Our main contribution is integrating dense feature rasterization into the novel-view synthesis, aligned with a visual foundation model. This yields strong semantics, going beyond basic RGB-D input, aiding both tracking and mapping accuracy. Unlike previous semantic SLAM approaches (which embed pre-defined class labels) FeatureSLAM enables entirely new downstream tasks via free-viewpoint, open-set segmentation. Across standard benchmarks, our method achieves real-time tracking, on par with state-of-the-art systems while improving tracking stability and map fidelity without prohibitive compute. Quantitatively, we obtain 9\% lower pose error and 8\% higher mapping accuracy compared to recent fixed-set SLAM baselines. Our results confirm that real-time feature-embedded SLAM, is not only valuable for enabling new downstream applications. It also improves the performance of the underlying tracking and mapping subsystems, providing semantic and language masking results that are on-par with offline 3DGS models, alongside state-of-the-art tracking, depth and RGB rendering.

翻译：我们提出了一种实时跟踪SLAM系统，该系统利用三维高斯溅射（3DGS）将高效相机跟踪与逼真的特征增强建图相统一。我们的主要贡献在于将密集特征栅格化整合到新视角合成中，并与视觉基础模型对齐。这产生了强大的语义信息，超越了基本的RGB-D输入，从而提升了跟踪与建图的精度。与以往基于预定义类别标签的语义SLAM方法不同，FeatureSLAM能够通过自由视角、开放集分割实现全新的下游任务。在标准基准测试中，我们的方法实现了实时跟踪，其性能与最先进系统相当，同时在无需高昂计算成本的情况下提升了跟踪稳定性与地图保真度。定量结果显示，与近期固定类别集的SLAM基线相比，我们的位姿误差降低了9%，建图精度提高了8%。我们的结果证实，实时特征嵌入SLAM不仅对实现新的下游应用具有重要价值，还能提升底层跟踪与建图子系统的性能，提供与离线3DGS模型相当的语义及语言掩码结果，同时保持最先进的跟踪、深度与RGB渲染能力。