# PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds

## TL;DR

PointFlowHop is a transparent, efficient scene flow estimation method for consecutive point clouds that outperforms deep learning approaches in accuracy, model size, training time, and computational complexity.

## Contribution

This work introduces PointFlowHop, a green, interpretable scene flow estimation method that decomposes the task into subtasks and demonstrates superior efficiency and transparency over deep learning models.

## Key findings

- Outperforms deep-learning methods on stereoKITTI and Argoverse datasets.
- Uses less training time and has a smaller model size.
- Requires significantly fewer FLOPs during inference.

## Abstract

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.