APSIPA Transactions on Signal and Information Processing > Vol 12 > Issue 4

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

Pranav Kadam, University of Southern California, Los Angeles, USA, pranavka@usc.edu , Jiahao Gu, University of Southern California, Los Angeles, USA, Shan Liu, Tencent Media Lab, Tencent America, USA, C.-C. Jay Kuo, University of Southern California, Los Angeles, USA
 
Suggested Citation
Pranav Kadam, Jiahao Gu, Shan Liu and C.-C. Jay Kuo (2023), "PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds", APSIPA Transactions on Signal and Information Processing: Vol. 12: No. 4, e103. http://dx.doi.org/10.1561/116.00000006

Publication Date: 03 Aug 2023
© 2023 P. Kadam, J. Gu, S. Liu and C.-C. Jay Kuo
 
Subjects
 
Keywords
3D scene flow estimationgreen learningunsupervised learningPointHop
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 212 times

In this article:
Introduction 
Related Work 
Proposed PointFlowHop Method 
Experiments 
Conclusion and Future Work 
References 

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.

DOI:10.1561/116.00000006

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Emerging AI Technologies for Smart Infrastructure
See the other articles that are part of this special issue.