F$^3$Loc: Fusion and Filtering for Floorplan Localization
This addresses indoor localization for robotics or AR/VR applications, offering a robust and efficient solution with incremental improvements in method and performance.
The paper tackles the problem of self-localization within a floorplan by proposing an efficient data-driven method that does not require per-map retraining or large image databases, achieving real-time performance and significantly outperforming state-of-the-art methods.
In this paper we propose an efficient data-driven solution to self-localization within a floorplan. Floorplan data is readily available, long-term persistent and inherently robust to changes in the visual appearance. Our method does not require retraining per map and location or demand a large database of images of the area of interest. We propose a novel probabilistic model consisting of an observation and a novel temporal filtering module. Operating internally with an efficient ray-based representation, the observation module consists of a single and a multiview module to predict horizontal depth from images and fuses their results to benefit from advantages offered by either methodology. Our method operates on conventional consumer hardware and overcomes a common limitation of competing methods that often demand upright images. Our full system meets real-time requirements, while outperforming the state-of-the-art by a significant margin.