实时融合特征与3D高斯溅射，提升地图精度与追踪稳定性。
FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time
- 将密集特征渲染融入新视角合成，结合视觉基础模型增强语义。
- 相比固定类别SLAM，位姿误差降9%，地图精度升8%。
- 支持自由视角开放集分割，适合需要语义理解的实时应用。
我们提出一种实时跟踪式SLAM系统，通过3D高斯溅射（3DGS）统一高效相机追踪与逼真特征增强的地图构建。核心贡献是将密集特征光栅化融入新视角合成，并与视觉基础模型对齐，从而获得强语义信息，超越传统RGB-D输入，同时提升追踪与建图精度。不同于以往嵌入预定义类别标签的语义SLAM，FeatureSLAM可实现自由视角、开放集分割，支持全新下游任务。在标准基准测试中，该方法达到实时追踪，性能与当前最优系统相当，且在不增加计算负担的前提下，显著提升追踪稳定性和地图保真度。定量结果显示，位姿误差降低9%，地图精度提高8%。结果表明，实时嵌入特征的SLAM不仅推动新应用发展，还提升了底层追踪与建图子系统的性能，其语义与语言掩码效果媲美离线3DGS模型，同时达到顶尖的追踪、深度与RGB渲染水平。
原文摘要 · Abstract (English)
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.
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。