LangGS-SLAM: 实时语言-特征高斯点云SLAM
LangGS-SLAM: Real-Time Language-Feature Gaussian Splatting SLAM
AI总结：
LangGS-SLAM通过实时语言-特征高斯点云SLAM实现高保真度的3D重建与语义映射。
摘要：
本文提出了一种RGB-D SLAM系统，能够在保持低延迟跟踪和映射的同时，重建出语言对齐的密集特征场。首先，我们引入了一个Top-K渲染流水线，这是一种高吞吐量且语义失真-free的方法，用于高效地渲染高维特征图。为了解决由此产生的语义-几何差异并缓解内存消耗，我们进一步设计了一种多标准地图管理策略，该策略在保留场景完整性的同时修剪冗余或不一致的高斯分布。最后，一个混合字段优化框架通过根据字段特性解耦其优化频率，共同优化几何和语义字段，在实时约束下进行联合细化。所提出的系统在几何保真度方面优于仅几何的基线，在语义保真度方面与离线方法相当，同时以15 FPS运行。我们的结果表明，具有密集、未压缩的语言对齐特征场的在线SLAM是可行且有效的，弥合了3D感知与基于语言的推理之间的差距。
英文摘要：
In this paper, we propose a RGB-D SLAM system that reconstructs a language-aligned dense feature field while sustaining low-latency tracking and mapping. First, we introduce a Top-K Rendering pipeline, a high-throughput and semantic-distortion-free method for efficiently rendering high-dimensional feature maps. To address the resulting semantic-geometric discrepancy and mitigate the memory consumption, we further design a multi-criteria map management strategy that prunes redundant or inconsistent Gaussians while preserving scene integrity. Finally, a hybrid field optimization framework jointly refines the geometric and semantic fields under real-time constraints by decoupling their optimization frequencies according to field characteristics. The proposed system achieves superior geometric fidelity compared to geometric-only baselines and comparable semantic fidelity to offline approaches while operating at 15 FPS. Our results demonstrate that online SLAM with dense, uncompressed language-aligned feature fields is both feasible and effective, bridging the gap between 3D perception and language-based reasoning.
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。
