AtLoc: Attention Guided Camera Localization
This addresses robustness issues in camera localization for applications like robotics and AR/VR, though it is an incremental improvement over existing attention-based methods.
The paper tackles the problem of robust single-image camera localization by using attention mechanisms to focus on geometrically stable features, achieving state-of-the-art performance on public indoor and outdoor benchmarks.
Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.