LEGO-SLAM：语言嵌入的高斯优化SLAM
LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM
AI总结：
研究将语言特征集成到基于3DGS的SLAM系统的问题，提出LEGO-SLAM框架，利用场景自适应自动编码器压缩语言嵌入，实现语言引导剪枝和回环检测，提升映射质量和跟踪精度，具备开放词汇能力且达15FPS。
摘要：
3D高斯点云渲染（3DGS）的进展使同时定位与地图构建（SLAM）系统能构建逼真地图，但缺乏语义理解。将语言特征集成到SLAM有挑战。我们提出LEGO-SLAM框架，在基于3DGS的SLAM系统中实现实时、开放词汇映射。核心是场景自适应自动编码器，将高维语言嵌入压缩到16维空间，减少内存并加速渲染。编码器可在线适应新场景，紧凑特征实现语言引导剪枝策略，减少高斯数量。还引入基于语言的回环检测方法。实验表明LEGO-SLAM在提供开放词汇能力的同时，实现了有竞争力的映射质量和跟踪精度。
英文摘要：
Recent advances in 3D Gaussian Splatting (3DGS) have enabled Simultaneous Localization and Mapping (SLAM) systems to build photorealistic maps. However, these maps lack the open-vocabulary semantic understanding required for robotic interaction. Integrating language features into SLAM remains a significant challenge, as storing high-dimensional features incurs excessive memory and rendering overhead, while existing methods with static models lack adaptability for novel environments. We propose LEGO-SLAM (Language-Embedded Gaussian Optimization SLAM), a framework that achieves real-time, open-vocabulary mapping within a 3DGS-based SLAM system. At the core of our method is a scene-adaptive autoencoder that distills high-dimensional language embeddings into a compact 16-dimensional feature space, reducing the memory per Gaussian and accelerating rendering. Unlike static approaches, our encoder adapts online to unseen scenes. These compact features also enable a language-guided pruning strategy that identifies semantic redundancy, reducing the map's Gaussian count by up to 58% while maintaining rendering quality. Furthermore, we introduce a language-based loop detection approach that reuses the language features already extracted for mapping, eliminating the need for a separate detection model. Experiments demonstrate that LEGO-SLAM achieves competitive mapping quality and tracking accuracy, all while providing open-vocabulary capabilities at 15 FPS. Our project page is available at https://lab-of-ai-and-robotics.github.io/LEGO-SLAM/
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。
