发表机构
State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FreeLoc提出在线RGB楼层平面定位框架，将楼层平面作为可直接查询的几何地图，通过在线几何查询和扩散辅助细化实现连续位姿估计，并构建在线似然支持时间融合，无需离线数据库，实现实时推理和最优性能。
AI 中文摘要
楼层平面图为室内定位提供了紧凑且广泛可用的几何地图，但现有的高性能基于楼层平面的方法仍将其转换为密集的场景特定离线数据库，将精度、存储和运行时间与离散化位姿空间的采样分辨率绑定。我们提出FreeLoc，一种在线基于RGB的楼层平面定位框架，将楼层平面视为可直接查询的几何地图。FreeLoc引入高效的在线几何查询和扩散辅助细化方案，通过即时楼层平面射线查询检索可行的位姿锚点，并将其细化为准确的连续位姿估计。对于序列定位，FreeLoc开发了一种在线似然构建策略，通过从粗采样候选和细化位姿假设构建似然，桥接单帧定位与概率时间融合，实现无需离线数据库的直方图滤波时间融合。实验展示了实时在线推理以及单帧和序列定位中的最先进性能，而真实世界结果验证了在室内机器人定位场景中的实际可部署性。
英文摘要
Floorplans provide compact and widely available geometric maps for indoor localization, but existing high-performing floorplan-based methods still convert them into dense scene-specific offline databases, tying accuracy, storage, and runtime to the sampling resolution of the discretized pose space. We present FreeLoc, an online RGB-based floorplan localization framework that treats the floorplan as a directly queryable geometric map. FreeLoc introduces an efficient online geometric querying and diffusion-aided refinement scheme, which retrieves plausible pose anchors through on-the-fly floorplan ray querying and refines them into accurate continuous pose estimates. For sequential localization, FreeLoc develops an online likelihood construction strategy that bridges single-frame localization and probabilistic temporal fusion by constructing likelihoods from coarse-sampled candidates and refined pose hypotheses, enabling histogram-filter-based temporal fusion without offline databases. Experiments demonstrate real-time online inference and state-of-the-art performance in both single-frame and sequential localization, while real-world results validate practical deployability in indoor robotic localization scenarios.
CommentsAccepted at the Conference on Robot Learning (CoRL) 2026. Project page: https://zju3dv.github.io/freeloc/
