DeFlow: Self-Supervised 3D Motion Estimation of Debris Flow

Liyuan Zhu, Yuru Jia, Shengyu Huang, Nicholas Meyer, Andreas Wieser, Konrad Schindler, Jordan Aaron; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 6508-6517

Abstract

Existing work on scene flow estimation focuses on autonomous driving and mobile robotics, while automated solutions are lacking for motion in nature, such as that exhibited by debris flows. We propose DeFlow, a model for 3D motion estimation of debris flows, together with a newly captured dataset. We adopt a novel multi-level sensor fusion architecture and self-supervision to incorporate the inductive biases of the scene. We further adopt a multi-frame temporal processing module to enable flow speed estimation over time. Our model achieves state-of-the-art optical flow and depth estimation on our dataset, and fully automates the motion estimation for debris flows. Source code and dataset are available at https://github.com/prs-eth/DeFlow.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2023_CVPR, author = {Zhu, Liyuan and Jia, Yuru and Huang, Shengyu and Meyer, Nicholas and Wieser, Andreas and Schindler, Konrad and Aaron, Jordan}, title = {DeFlow: Self-Supervised 3D Motion Estimation of Debris Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {6508-6517} }