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. The source code and dataset are available at project page. Show more
Publication status
publishedExternal links
Book title
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Pages / Article No.
Publisher
IEEEEvent
Subject
Computer Vision and Pattern Recognition (cs.CV); FOS: Computer and information sciencesOrganisational unit
03964 - Wieser, Andreas / Wieser, Andreas
03886 - Schindler, Konrad / Schindler, Konrad
09797 - Aaron, Jordan / Aaron, Jordan
Funding
193081 - Measuring and Modelling Catastrophic Landslides and Debris Flows (SNF)
Related publications and datasets
Is new version of: https://doi.org/10.48550/ARXIV.2304.02569
More
Show all metadata
ETH Bibliography
yes
Altmetrics