SeFlow: A Self-Supervised Scene Flow Method in Autonomous Driving

TL;DR

SeFlow introduces a self-supervised scene flow estimation method for autonomous driving that improves accuracy by classifying point motion types and enforcing object-level consistency, achieving state-of-the-art results without labeled data.

Contribution

The paper presents SeFlow, a novel self-supervised scene flow approach that incorporates dynamic classification and object-level constraints for enhanced point cloud motion estimation.

Findings

Achieves state-of-the-art performance on Argoverse 2 and Waymo datasets.

Operates in real-time for autonomous driving applications.

Effectively handles point distribution imbalance and object-level motion constraints.

Abstract

Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is open-sourced at https://github.com/KTH-RPL/SeFlow along with trained model weights.