FeatureSLAM: 实时特征增强的3D高斯点云SLAM
FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time
AI总结：
本文提出一种实时SLAM系统，结合高效相机跟踪与逼真特征映射，利用3D高斯点云技术。核心贡献是将密集特征栅格化整合到新视角合成中，提升语义准确性，优于传统RGB-D输入，增强跟踪与映射精度。
摘要：
我们提出了一种实时跟踪SLAM系统，通过3D高斯点云技术将高效相机跟踪与逼真特征增强的映射相结合。主要贡献是将密集特征栅格化整合到新视角合成中，与视觉基础模型对齐。这带来了更强的语义信息，超越基本RGB-D输入，有助于跟踪和映射精度。与以往的语义SLAM方法（嵌入预定义类别标签）不同，FeatureSLAM通过自由视角、开放集分割支持全新的下游任务。在标准基准上，我们的方法实现了实时跟踪，性能与最新系统相当，同时在跟踪稳定性和地图保真度上有所提升，且计算成本可控。定量结果表明，相比最近的固定集SLAM基线，姿态误差降低了9%，映射准确性提高了8%。我们的结果证实，实时特征嵌入SLAM不仅对启用新下游应用有价值，还提升了底层跟踪和映射子系统的性能，提供了与离线3DGS模型相当的语义和语言遮蔽结果，同时具备最先进的跟踪、深度和RGB渲染性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
