面向零样本具身导航与推理的多尺度高斯-语言地图
Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning
把每个语义单元同时存成自然语言描述和 3D 高斯，用高斯泼溅按需渲染任务相关视角，为大模型提供免训练的对齐接口；做具身导航或场景问答时可直接复用这种「语言-高斯」双模态地图表示，替代需要额外训练投影层的语义地图。
原文依据 a dual-modality interface where each semantic unit jointly stores a natural language description and a 3D Gaussian representation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论理解环境的几何与语义结构对具身智能体至关重要。现有语义建图方法在显式几何与多尺度语义之间做取舍，且缺乏面向大模型的原生接口，因而需要额外训练特征投影以实现语义对齐。为此，我们提出多尺度高斯-语言地图（GLMap），引入三项关键设计：（1）显式几何；（2）覆盖实例级与区域级概念的多尺度语义；（3）双模态接口，其中每个语义单元同时存储自然语言描述与三维高斯表示。三维高斯借助高斯泼溅实现紧凑存储与任务相关图像的快速渲染。为支持高效的增量式构建，我们进一步提出高斯估计器，可从稠密点云解析地推导高斯参数，无需基于梯度的优化。在 ObjectNav、InstNav 与 SQA 任务上的实验表明，GLMap 有效增强了目标定位与上下文推理能力，同时以零样本方式与大模型方法保持兼容。
英文原文摘要 1181 字符
Understanding the geometric and semantic structure of environments is essential for embodied agents. Existing semantic mapping methods trade off between explicit geometry and multi-scale semantics,and lack a native interface for large models, thus requiring additional training of feature projection for semantic alignment. To this end, we propose the multi-scale Gaussian-Language Map (GLMap), which introduces three key designs: (1) explicit geometry, (2) multi-scale semantics covering both instance and region level concepts, and (3) a dual-modality interface where each semantic unit jointly stores a natural language description and a 3D Gaussian representation. The 3D Gaussians enable compact storage and fast rendering of task-relevant images via Gaussian splatting. To enable efficient incremental construction, we further propose a Gaussian Estimator that analytically derives Gaussian parameters from dense point clouds without gradient-based optimization. Experiments on ObjectNav, InstNav, and SQA tasks show that GLMap effectively enhances target localization and contextual reasoning, while remaining compatible with large-model-based methods in a zero-shot manner.