用自然语言精确定位室内位置，无需摄像头且保护隐私。
LangLoc: "Tell Me What You See"
- 三阶段流程：先找场景，再估位置方向，最后用问答消除歧义。
- 定位误差中位数仅0.95米，场景召回率比之前高8个百分点。
- 适合需要隐私保护的室内导航、智能助手等应用。
我们解决从自然语言中进行细粒度室内定位的问题：给定对周围环境的自由描述，估计观察者在已知3D环境中的2D位置和朝向。语言查询轻量、保护隐私且无需摄像头——但此前工作仅能粗粒度检索场景，无法分辨场景内具体姿态。我们提出LangLoc，一个三阶段流程：(i) 使用双分支GATv2编码器结合CLIP语义特征检索正确场景，Top-1召回率提升8个百分点；(ii) 通过射线投射物体可见性对密集地板网格打分，实现0.95米中位数定位误差；(iii) 通过贝叶斯对话模块提出针对性是/否问题，迭代更新姿态后验直至精确定位。为支持该任务，我们构建了一个包含超过13,000个姿态标注的自然语言描述数据集，覆盖1,300多个室内3D扫描。
原文摘要 · Abstract (English)
We tackle fine-grained indoor localization from natural language: given a free-form description of one's surroundings, estimate the observer's 2D position and heading within a known 3D environment. Language queries are lightweight, privacy-preserving, and need no camera - yet prior work stops at coarse scene retrieval and cannot resolve an intra-scene pose. We close this gap with LangLoc, a three-stage pipeline that (i) retrieves the correct scene via a dual-branch GATv2 encoder with CLIP semantic features, surpassing the previous best by 8 percentage points in Top-1 recall; (ii) estimates position and heading by scoring a dense floor grid through ray-cast object visibility, reaching a median error of 0.95 m; and (iii) resolves residual ambiguity through a Bayesian dialog module that asks targeted yes/no questions and updates a pose posterior until the location is pinpointed. To support this task we contribute a benchmark of $13{,}000{+}$ pose-indexed natural-language descriptions over $1{,}300{+}$ indoor 3D scans.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。