papers AI Learner
The Github is limit! Click to go to the new site.

Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

2019-04-03
Fei Xue, Xin Wang, Shunkai Li, Qiuyuan Wang, Junqiu Wang, Hongbin Zha

Abstract

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.01892

PDF

https://arxiv.org/pdf/1904.01892


Similar Posts

Comments