Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion

Alex Zihao Zhu, Liangzhe Yuan, Kenneth Chaney, Kostas Daniilidis; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 989-997

Abstract


In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the form of a discretized volume that maintains the temporal distribution of the events, which we pass through a neural network to predict the motion of the events. This motion is used to attempt to remove any motion blur in the event image. We then propose a loss function applied to the motion compensated event image that measures the motion blur in this image. We train two networks with this framework, one to predict optical flow, and one to predict egomotion and depths, and evaluate these networks on the Multi Vehicle Stereo Event Camera dataset, along with qualitative results from a variety of different scenes.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhu_2019_CVPR,
author = {Zhu, Alex Zihao and Yuan, Liangzhe and Chaney, Kenneth and Daniilidis, Kostas},
title = {Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}