FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinement

2026-10-04

AI Summary

This study addresses the reliance of indoor localization on offline databases and its accuracy limitations imposed by discrete sampling resolution. We propose an online RGB localization framework that introduces a novel geometry-based query mechanism eliminating the need for offline databases. Specifically, floor plans are treated as queryable maps, enabling real-time pixel-ray casting to obtain pose anchors. Furthermore, diffusion models facilitate continuous pose refinement and likelihood construction, while a histogram filter performs temporal probabilistic fusion. The proposed approach achieves state-of-the-art performance on both single-frame and sequential localization tasks. It supports real-time inference, and its deployment feasibility has been validated in real-world robotic scenarios.

Abstract

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.

Problem

• indoor localization
• floorplan-based localization
• online pose estimation
• sequential localization

Innovation

• Floorplan Localization
• Diffusion-Aided Refinement
• Online Geometric Querying
• Histogram Filter
• Indoor Robot Localization