AtLoc: Attention Guided Camera Localization

Authors

  • Bing Wang University of Oxford
  • Changhao Chen University of Oxford
  • Chris Xiaoxuan Lu University of Oxford
  • Peijun Zhao University of Oxford
  • Niki Trigoni University of Oxford
  • Andrew Markham University of Oxford

DOI:

https://doi.org/10.1609/aaai.v34i06.6608

Abstract

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.

Downloads

Published

2020-04-03

How to Cite

Wang, B., Chen, C., Xiaoxuan Lu, C., Zhao, P., Trigoni, N., & Markham, A. (2020). AtLoc: Attention Guided Camera Localization. Proceedings of the AAAI Conference on Artificial Intelligence, 34(06), 10393-10401. https://doi.org/10.1609/aaai.v34i06.6608

Issue

Section

AAAI Technical Track: Robotics