Hier-SLAM：利用分层类别化高斯泼溅实现SLAM中的语义规模化扩展
Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splatting
AI总结：
Hier-SLAM提出分层类别化高斯泼溅表示，将大语言模型语义信息紧凑编码到3D高斯泼溅中，实现精确语义建图、2倍加速和500+语义类别的规模化扩展能力。
摘要：
我们提出Hier-SLAM，一种具有新颖分层类别化表示的语义3D高斯泼溅SLAM方法，能够实现精确的全局3D语义建图、规模化扩展能力以及在3D世界中进行显式语义标签预测。语义SLAM系统中的参数使用量随着环境复杂度的增长而显著增加，这使得场景理解变得尤为困难且成本高昂。为解决这一问题，我们引入一种新颖的分层表示，利用大语言模型（LLMs）的能力，将语义信息以紧凑形式编码到3D高斯泼溅中。我们进一步引入一种新颖的语义损失，旨在通过层级间和跨层级优化来优化分层语义信息。此外，我们增强了整个SLAM系统，从而改善了跟踪和建图性能。我们的Hier-SLAM在建图和跟踪精度上均优于现有稠密SLAM方法，同时实现了2倍的运行速度提升。此外，与现有方法相比，它在语义渲染性能上达到同等水平，同时显著降低了存储和训练时间需求。渲染FPS在包含语义信息时令人印象深刻地达到2,000，不含语义信息时达到3,000。最值得注意的是，它展示了处理包含超过500个语义类别的复杂真实世界场景的能力，突显了其宝贵的规模化扩展能力。开源代码可在https://github.com/LeeBY68/Hier-SLAM获取。
英文摘要：
We propose Hier-SLAM, a semantic 3D Gaussian Splatting SLAM method featuring a novel hierarchical categorical representation, which enables accurate global 3D semantic mapping, scaling-up capability, and explicit semantic label prediction in the 3D world. The parameter usage in semantic SLAM systems increases significantly with the growing complexity of the environment, making it particularly challenging and costly for scene understanding. To address this problem, we introduce a novel hierarchical representation that encodes semantic information in a compact form into 3D Gaussian Splatting, leveraging the capabilities of large language models (LLMs). We further introduce a novel semantic loss designed to optimize hierarchical semantic information through both inter-level and cross-level optimization. Furthermore, we enhance the whole SLAM system, resulting in improved tracking and mapping performance. Our \MethodName{} outperforms existing dense SLAM methods in both mapping and tracking accuracy, while achieving a 2x operation speed-up. Additionally, it achieves on-par semantic rendering performance compared to existing methods while significantly reducing storage and training time requirements. Rendering FPS impressively reaches 2,000 with semantic information and 3,000 without it. Most notably, it showcases the capability of handling the complex real-world scene with more than 500 semantic classes, highlighting its valuable scaling-up capability. The open-source code is available at https://github.com/LeeBY68/Hier-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。
