SlugTrails：大型建筑楼层平面定位的自我中心基准
SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings
浏览论文内容
中文总结 AI 辅助
针对大型建筑自我中心视觉的楼层平面定位基准SlugTrails，通过多协议评估发现预训练模型效果差，微调显著提升性能，表明数据是当前瓶颈。
中文摘要 AI 辅助
基于楼层平面的室内视觉定位能够实现无基础设施的定位，但大多数方法是在小型住宅环境中开发和评估的，这与实际部署中的大型公共建筑不同。我们提出了SlugTrails，一个针对大型室内空间、在真实自我中心感知条件下的楼层平面定位基准：跨越三座校园建筑和六个楼层的30 Hz Aria眼镜记录（楼层平面轮廓面积为22089平方米），带有语义类别和流通空间掩码的CAD派生楼层平面，以及使用激光测量锚点对齐到楼层平面坐标系的轨迹。一个协议涵盖了在有限视野下收集几何信息的三种实用方式——单次行走帧、静态多视角扫描和带里程计的行走流——因此为不同机制设计的方法可以在相同的建筑和真实地面真值上进行比较。评估五种代表性的几何和基于学习的系统在其原生传感配置下，我们发现官方发布的预训练权重（stock checkpoints）在SlugTrails上几乎为零（在行走单帧上最多为0.004 R@1m30°），而在SlugTrails上微调则提高了每个可训练家族在所有三个任务上的性能（例如，F³Loc从0.0提高到0.141（单帧），从0.03提高到0.66（序列）），且随着观测累积，增益不断增加。相同的微调权重也提高了在LaMAR上的跨数据集泛化能力，而无需在LaMAR上训练（F³Loc的序列R@1m从0.048提高到0.143，UnLoc从0.063提高到0.127），而仅在SlugTrails上从头训练则远低于从预训练权重微调的效果——这证明楼层平面定位目前受限于室内数据而非架构。我们在以下网址发布了数据集、协议和工具：此https URL。
英文摘要
Floor-plan-based indoor visual localization enables infrastructure-free positioning, but most methods are developed and evaluated in small residential environments unlike the large public buildings of real deployment. We introduce SlugTrails, a floor plan localization benchmark for large indoor spaces under realistic egocentric sensing: $30$ Hz Aria glasses recordings across three campus buildings and six floors ($22089$ m$^2$ of floor plan outline), CAD-derived floor plans with semantic classes and circulation space masks, and trajectories aligned into the floor plan frame using laser-surveyed anchors. One protocol covers three practical ways of gathering geometry under a limited field of view -- a single walking frame, a stationary multi-view sweep, and a walking stream with odometry -- so methods designed for different regimes are compared on the same buildings and ground truth. Evaluating five representative geometric and learned systems under their native sensing configurations, we find that stock checkpoints (official released weights) are near zero on SlugTrails (at most $0.004$ R@1m30$^{\circ}$ on walking single frames), while fine-tuning on SlugTrails improves every trainable family on all three tasks (e.g., F$^3$Loc $0.0 \rightarrow 0.141$ single-frame and $0.03 \rightarrow 0.66$ sequential), with gains compounding as observations accumulate. The same fine-tuned weights also improve cross-dataset generalization on LaMAR with no LaMAR training (sequential R@1m $0.048 \rightarrow 0.143$ for F$^3$Loc and $0.063 \rightarrow 0.127$ for UnLoc), whereas train-from-scratch on SlugTrails alone stays far below fine-tuning from stock weights -- evidence that floor plan localization is currently limited by indoor data rather than by architecture. We release the dataset, protocols, and tools at https://github.com/Head-inthe-Cloud/SlugTrails.
发表机构
- University of California, Santa Cruz（加州大学圣克鲁兹分校）
机构由 AI 辅助整理，请以论文原文为准。
