UnLoc: Leveraging Depth Uncertainties for Floorplan Localization
This addresses the problem of robust indoor localization for robotics or AR applications, but it is incremental as it builds on existing floorplan-based methods by improving uncertainty handling and generalization.
The paper tackles camera localization in floorplans by introducing a probabilistic model that incorporates depth uncertainty and uses pre-trained depth models, achieving 2.7 times higher recall on long sequences and 16.7 times higher on short ones compared to state-of-the-art methods.
We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to changes in visual appearance. We address key limitations of recent methods, such as the lack of uncertainty modeling in depth predictions and the necessity for custom depth networks trained for each environment. We introduce a novel probabilistic model that incorporates uncertainty estimation, modeling depth predictions as explicit probability distributions. By leveraging off-the-shelf pre-trained monocular depth models, we eliminate the need to rely on per-environment-trained depth networks, enhancing generalization to unseen spaces. We evaluate UnLoc on large-scale synthetic and real-world datasets, demonstrating significant improvements over existing methods in terms of accuracy and robustness. Notably, we achieve $2.7$ times higher localization recall on long sequences (100 frames) and $16.7$ times higher on short ones (15 frames) than the state of the art on the challenging LaMAR HGE dataset.