Guided Feature Selection for Deep Visual Odometry
This addresses visual odometry for robotics and autonomous systems, representing an incremental improvement with a novel dual-branch approach.
The paper tackles visual odometry by proposing an end-to-end architecture with guided feature selection using deep convolutional recurrent neural networks, achieving state-of-the-art performance on KITTI and ICL_NUIM benchmarks for camera pose recovery.
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-the-art model- and learning-based methods for both decoupled and joint camera pose recovery.