DeFlow: Decoder of Scene Flow Network in Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Qingwen, Yang, Yi, Fang, Heng, Geng, Ruoyu, Jensfelt, Patric
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917577412837376
author Zhang, Qingwen
Yang, Yi
Fang, Heng
Geng, Ruoyu
Jensfelt, Patric
author_facet Zhang, Qingwen
Yang, Yi
Fang, Heng
Geng, Ruoyu
Jensfelt, Patric
contents Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in recovering those features for scene flow tasks. Our paper introduces DeFlow which enables a transition from voxel-based features to point features using Gated Recurrent Unit (GRU) refinement. To further enhance scene flow estimation performance, we formulate a novel loss function that accounts for the data imbalance between static and dynamic points. Evaluations on the Argoverse 2 scene flow task reveal that DeFlow achieves state-of-the-art results on large-scale point cloud data, demonstrating that our network has better performance and efficiency compared to others. The code is open-sourced at https://github.com/KTH-RPL/deflow.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16122
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DeFlow: Decoder of Scene Flow Network in Autonomous Driving
Zhang, Qingwen
Yang, Yi
Fang, Heng
Geng, Ruoyu
Jensfelt, Patric
Computer Vision and Pattern Recognition
Robotics
Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in recovering those features for scene flow tasks. Our paper introduces DeFlow which enables a transition from voxel-based features to point features using Gated Recurrent Unit (GRU) refinement. To further enhance scene flow estimation performance, we formulate a novel loss function that accounts for the data imbalance between static and dynamic points. Evaluations on the Argoverse 2 scene flow task reveal that DeFlow achieves state-of-the-art results on large-scale point cloud data, demonstrating that our network has better performance and efficiency compared to others. The code is open-sourced at https://github.com/KTH-RPL/deflow.
title DeFlow: Decoder of Scene Flow Network in Autonomous Driving
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2401.16122