VLM-Loc：基于视觉语言模型的点云地图定位
VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models
将点云转为BEV图像和场景图，利用VLM的跨模态推理能力实现文本到点云的定位，为3D场景理解提供可解释的空间推理新范式。
原文依据 we transform point clouds into bird's-eye-view (BEV) images and scene graphs that jointly encode geometric and semantic context
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到点云（T2P）定位旨在从自然语言描述中推断三维点云地图内的精确空间位置，反映了人类通过语言感知和沟通空间布局的方式。然而，现有方法主要依赖浅层的文本-点云对应关系，缺乏有效的空间推理，限制了其在复杂环境中的准确性。为解决这一局限，我们提出VLM-Loc，一个利用大型视觉语言模型（VLM）的空间推理能力进行T2P定位的框架。具体而言，我们将点云转换为鸟瞰图（BEV）图像和场景图，联合编码几何与语义上下文，为VLM提供结构化输入，以学习桥接语言与空间语义的跨模态表征。在这些表征之上，我们引入部分节点分配机制，显式地将文本线索与场景图节点关联，从而实现可解释的空间推理以进行准确定位。为促进跨多样场景的系统评估，我们提出了CityLoc，一个基于多源点云构建的基准，用于细粒度T2P定位。在CityLoc上的实验表明，VLM-Loc相比最优方法实现了更高的准确性和鲁棒性。我们的代码、模型和数据集可在https://github.com/MCG-NKU/nku-3d-vision仓库获取。
英文原文摘要 1428 字符
Text-to-point-cloud (T2P) localization aims to infer precise spatial positions within 3D point cloud maps from natural language descriptions, reflecting how humans perceive and communicate spatial layouts through language. However, existing methods largely rely on shallow text-point cloud correspondence without effective spatial reasoning, limiting their accuracy in complex environments. To address this limitation, we propose VLM-Loc, a framework that leverages the spatial reasoning capability of large vision-language models (VLMs) for T2P localization. Specifically, we transform point clouds into bird's-eye-view (BEV) images and scene graphs that jointly encode geometric and semantic context, providing structured inputs for the VLM to learn cross-modal representations bridging linguistic and spatial semantics. On top of these representations, we introduce a partial node assignment mechanism that explicitly associates textual cues with scene graph nodes, enabling interpretable spatial reasoning for accurate localization. To facilitate systematic evaluation across diverse scenes, we present CityLoc, a benchmark built from multi-source point clouds for fine-grained T2P localization. Experiments on CityLoc demonstrate VLM-Loc achieves superior accuracy and robustness compared to state-of-the-art methods. Our code, model, and dataset are available at \href https://github.com/MCG-NKU/nku-3d-vision repository .