SSF: Sparse Long-Range Scene Flow for Autonomous Driving

TL;DR

This paper introduces SSF, a sparse convolution-based pipeline for long-range scene flow estimation in autonomous driving, addressing scalability issues of previous dense methods and achieving state-of-the-art results.

Contribution

The paper proposes a novel sparse scene flow method using sparse convolutions and a feature fusion scheme to improve long-range scene flow estimation.

Findings

Achieves state-of-the-art results on Argoverse2 dataset.

Effectively handles sparse, long-range point cloud data.

Introduces a range-wise metric emphasizing distant points.

Abstract

Scene flow enables an understanding of the motion characteristics of the environment in the 3D world. It gains particular significance in the long-range, where object-based perception methods might fail due to sparse observations far away. Although significant advancements have been made in scene flow pipelines to handle large-scale point clouds, a gap remains in scalability with respect to long-range. We attribute this limitation to the common design choice of using dense feature grids, which scale quadratically with range. In this paper, we propose Sparse Scene Flow (SSF), a general pipeline for long-range scene flow, adopting a sparse convolution based backbone for feature extraction. This approach introduces a new challenge: a mismatch in size and ordering of sparse feature maps between time-sequential point scans. To address this, we propose a sparse feature fusion scheme, that augments the feature maps with virtual voxels at missing locations. Additionally, we propose a range-wise metric that implicitly gives greater importance to faraway points. Our method, SSF, achieves state-of-the-art results on the Argoverse2 dataset, demonstrating strong performance in long-range scene flow estimation. Our code will be released at https://github.com/KTH-RPL/SSF.git.