A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition
This work provides a method to reduce the data collection burden for autonomous driving and mobile robotics developers working on 3D point cloud place recognition, offering an incremental improvement.
This paper addresses the challenge of training 3D point cloud place recognition models due to the difficulty of obtaining real-world data. They propose a registration-aided domain adaptation network, trained on a synthetic dataset, which achieves state-of-the-art or comparable performance on the real-world Oxford RobotCar dataset.
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset.