PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds
This work addresses efficient and interpretable scene flow estimation for applications like autonomous driving, but it is incremental as it builds on existing green learning pipelines.
The authors tackled 3D scene flow estimation from consecutive point clouds by proposing PointFlowHop, which decomposes the task into subtasks like ego-motion compensation and object association, resulting in outperforming deep-learning methods with a small model size and less training time, as demonstrated on stereoKITTI and Argoverse datasets.
An efficient 3D scene flow estimation method called PointFlowHop is proposed in this work. PointFlowHop takes two consecutive point clouds and determines the 3D flow vectors for every point in the first point cloud. PointFlowHop decomposes the scene flow estimation task into a set of subtasks, including ego-motion compensation, object association and object-wise motion estimation. It follows the green learning (GL) pipeline and adopts the feedforward data processing path. As a result, its underlying mechanism is more transparent than deep-learning (DL) solutions based on end-to-end optimization of network parameters. We conduct experiments on the stereoKITTI and the Argoverse LiDAR point cloud datasets and demonstrate that PointFlowHop outperforms deep-learning methods with a small model size and less training time. Furthermore, we compare the Floating Point Operations (FLOPs) required by PointFlowHop and other learning-based methods in inference, and show its big savings in computational complexity.