Guided Feature Selection for Deep Visual Odometry

Fei Xue, Hongbin Zha

Abstract:

We present a novel end-to-end visual odometry architecture
with guided feature selection based on deep convolutional recurrent neural networks. Different from current monocular visual odometry methods, our approach is established on the intuition that features contribute
discriminately to different motion patterns. Specifically, we propose a
dual-branch recurrent network to learn the rotation and translation separately by leveraging current Convolutional Neural Network (CNN) for
feature representation and Recurrent Neural Network (RNN) for image
sequence reasoning. To enhance the ability of feature selection, we further introduce an effective context-aware guidance mechanism to force
each branch to distill related information for specific motion pattern
explicitly. Experiments demonstrate that on the prevalent KITTI and
ICL NUIM benchmarks, our method outperforms current state-of-theart model- and learning-based methods for both decoupled and joint
camera pose recovery.