English

Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision

Computer Vision and Pattern Recognition 2023-03-20 v3 Artificial Intelligence Machine Learning Robotics

Abstract

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our approach is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such redundancy implicitly provides various forms of supervision cues to the radar scene flow estimation. Specifically, we introduce a multi-task model architecture for the identified cross-modal learning problem and propose loss functions to opportunistically engage scene flow estimation using multiple cross-modal constraints for effective model training. Extensive experiments show the state-of-the-art performance of our method and demonstrate the effectiveness of cross-modal supervised learning to infer more accurate 4D radar scene flow. We also show its usefulness to two subtasks - motion segmentation and ego-motion estimation. Our source code will be available on https://github.com/Toytiny/CMFlow.

Keywords

Cite

@article{arxiv.2303.00462,
  title  = {Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision},
  author = {Fangqiang Ding and Andras Palffy and Dariu M. Gavrila and Chris Xiaoxuan Lu},
  journal= {arXiv preprint arXiv:2303.00462},
  year   = {2023}
}

Comments

10 pages, 7 figures. Accepted by CVPR 2023. See our code at https://github.com/Toytiny/CMFlow. Supplementary materials can be found at https://drive.google.com/file/d/1Iewcqnjzecge2ePBM8k2tg-85LX5xs3N/view

R2 v1 2026-06-28T08:53:56.687Z