Point Cloud based Hierarchical Deep Odometry Estimation
This addresses the challenge of processing point clouds for odometry in autonomous driving, but appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of odometry estimation in driving scenarios using raw point cloud data, proposing a hierarchical deep model and an LSTM-based variation, and reports comprehensive evaluation against state-of-the-art methods.
Processing point clouds using deep neural networks is still a challenging task. Most existing models focus on object detection and registration with deep neural networks using point clouds. In this paper, we propose a deep model that learns to estimate odometry in driving scenarios using point cloud data. The proposed model consumes raw point clouds in order to extract frame-to-frame odometry estimation through a hierarchical model architecture. Also, a local bundle adjustment variation of this model using LSTM layers is implemented. These two approaches are comprehensively evaluated and are compared against the state-of-the-art.