Point Cloud Densification Based on Scene Flow Estimation and Kalman Refinement

Point cloud densification is an effective measure to alleviate the sparseness of point clouds. In 3-D vision, the positional relationship of multiframe point clouds is applied to point cloud densification research to explain the rationality of the source of supplementary points. Among them, scene flow estimation is effective for dynamic scenes. However, scene flow estimation of long-sequence dynamic point clouds is prone to cumulative positioning errors. In order to solve this problem, this article proposes to correct the scene flow estimation results from a timing perspective based on Kalman filtering. Specifically, the scene flow estimation model is first optimized according to the pyramid structure to improve the reliability of point cloud feature extraction. Then, combined with the temporal relationship of the point clouds in the previous and later frames, the point cloud is reconstructed uniformly to complete the densification of the point cloud. Finally, the densified point cloud is applied to the 3-D detection task. Results on the KITTI 3-D tracking dataset show that the point cloud densification method based on scene flow estimation can effectively improve the performance of LiDAR-only detectors.