SSF: Sparse Long-Range Scene Flow for Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khoche, Ajinkya, Zhang, Qingwen, Sanchez, Laura Pereira, Asefaw, Aron, Mansouri, Sina Sharif, Jensfelt, Patric
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915128091344896
author Khoche, Ajinkya
Zhang, Qingwen
Sanchez, Laura Pereira
Asefaw, Aron
Mansouri, Sina Sharif
Jensfelt, Patric
author_facet Khoche, Ajinkya
Zhang, Qingwen
Sanchez, Laura Pereira
Asefaw, Aron
Mansouri, Sina Sharif
Jensfelt, Patric
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17821
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SSF: Sparse Long-Range Scene Flow for Autonomous Driving
Khoche, Ajinkya
Zhang, Qingwen
Sanchez, Laura Pereira
Asefaw, Aron
Mansouri, Sina Sharif
Jensfelt, Patric
Computer Vision and Pattern Recognition
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.
title SSF: Sparse Long-Range Scene Flow for Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.17821