Hier-SLAM++：具有分层类别高斯溅射的神经符号语义SLAM
Hier-SLAM++: Neuro-Symbolic Semantic SLAM with a Hierarchically Categorical Gaussian Splatting
AI总结：
Hier-SLAM++提出一种神经符号语义三维高斯溅射SLAM方法，通过分层类别表示紧凑编码语义与几何信息，支持RGB-D和单目输入，实现准确姿态估计与全局语义映射，性能优越且降低存储和训练成本。
摘要：
我们提出了Hier-SLAM++，一种全面的神经符号语义三维高斯溅射SLAM方法，支持RGB-D和单目输入，具有先进的分层类别表示，能够实现准确的姿态估计以及全局三维语义映射。随着环境复杂性的增加，语义SLAM系统中的参数使用量显著增长，使得场景理解变得特别具有挑战性和昂贵。为了解决这个问题，我们引入了一种新颖的分层表示，将语义和几何信息以紧凑形式编码到三维高斯溅射中，利用大型语言模型（LLMs）以及三维生成模型的能力。通过利用所提出的分层树结构，语义信息以符号方式表示并以端到端方式学习。我们进一步引入了一种先进的语义损失，旨在通过层内和层间优化来优化分层语义信息。此外，我们提出了一种改进的SLAM系统，使用前馈模型支持RGB-D和单目输入。据我们所知，这是第一个语义单目高斯溅射SLAM系统，显著降低了对三维语义理解的传感器要求，并拓宽了语义高斯SLAM系统的适用性。我们在合成和真实世界数据集上进行了实验，展示了与最先进方法相比优越或相当的性能，同时显著减少了存储和训练时间需求。我们的项目页面可在以下网址获得：https://hierslampp.github.io/
英文摘要：
We propose Hier-SLAM++, a comprehensive Neuro-Symbolic semantic 3D Gaussian Splatting SLAM method with both RGB-D and monocular input featuring an advanced hierarchical categorical representation, which enables accurate pose estimation as well as global 3D semantic mapping. The parameter usage in semantic SLAM systems increases significantly with the growing complexity of the environment, making scene understanding particularly challenging and costly. To address this problem, we introduce a novel hierarchical representation that encodes both semantic and geometric information in a compact form into 3D Gaussian Splatting, leveraging the capabilities of large language models (LLMs) as well as the 3D generative model. By utilizing the proposed hierarchical tree structure, semantic information is symbolically represented and learned in an end-to-end manner. We further introduce an advanced semantic loss designed to optimize hierarchical semantic information through both Intra-level and Inter-level optimizations. Additionally, we propose an improved SLAM system to support both RGB-D and monocular inputs using a feed-forward model. To the best of our knowledge, this is the first semantic monocular Gaussian Splatting SLAM system, significantly reducing sensor requirements for 3D semantic understanding and broadening the applicability of semantic Gaussian SLAM system. We conduct experiments on both synthetic and real-world datasets, demonstrating superior or on-par performance with state-of-the-art methods, while significantly reducing storage and training time requirements. Our project page is available at: https://hierslampp.github.io/
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。
