论文/arXiv 2608.07074·2 个月前

M2-SMap：基于分层多模型表示的内存高效语义建图

M2-SMap面向资源受限机器人稠密点云内存增长问题，采用分层多模型语义表示，并在三条RGB-D序列上验证实时性与紧凑性。

AI 整理

• 感知与导航

原文链接：M2-SMap: Memory-Efficient Semantic Mapping with Hierarchical Multi-Model Representation（arXiv 2608.07074 · 发布日期：2026-08-07）

M2-SMap: Memory-Efficient Semantic Mapping with Hierarchical Multi-Model Representation

M2-SMap面向资源受限机器人稠密点云内存增长问题，采用分层多模型语义表示，并在三条RGB-D序列上验证实时性与紧凑性。

核心要点

• 稠密点云地图随场景规模快速增大，单模型表达固定，多模型又易受局部几何主导而产生粘连。
• 方法将RGB-D点云分解为紧凑高斯组件，并用投影引导语义标注为组件分配实例身份。
• 框架结合对象感知高斯融合与多尺度特征提取，分别表示平面、语义对象和复杂残余结构。
• 三条RGB-D序列实验显示其不低于29.37 Hz，基元数量最低且对象间粘连测量降为0。

验证范围与局限：验证范围为三条RGB-D序列。

英文摘要 (Abstract)

Dense point cloud maps, as a typically used mapping representation, are difficult to deploy on resource-constrained robots because their memory consumption grows rapidly with scene scale. Although compact single-model representations reduce memory cost, their fixed geometric expressiveness is insufficient for structurally diverse environments. Existing multi-model methods improve representational flexibility, yet their feature extraction and model selection are often dominated by local geometry, which can cause overfitting and adhesion between objects. To address these issues, this paper presents M2-SMap, a memory-efficient semantic mapping framework based on hierarchical multi-model representation. First, a hierarchical geometric decomposition partitions RGB-D point clouds into compact Gaussian components. Then, a projection-guided semantic annotation mechanism assigns instance identities to each component. Subsequently, these annotations are incorporated into an object-aware Gaussian fusion strategy. Furthermore, a multi-scale feature extraction strategy separates large planar regions, semantic objects, and complex residual structures, which are respectively represented by bounded planes, object-level superquadrics, and GMM primitives. Experiments on three RGB-D sequences show that M2-SMap runs in real time at no less than 29.37 Hz while achieving the lowest primitive count, with an average reduction of 18.7% over the best baseline. It also reduces the mean per-frame number of measured inter-object adhesion cases from 2.808 to 0, demonstrating efficient and semantically consistent scene representation.

作者：Qi Deng, ZhongLai Wang, Yuan Gao, Wei Dong

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2608.07074：M2-SMap: Memory-Efficient Semantic Mapping with Hierarchical Multi-Model Representation访问 2026-10-21