Back to Search Start Over

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

Authors :
Shen, Tianwei
Luo, Zixin
Zhou, Lei
Deng, Hanyu
Zhang, Runze
Fang, Tian
Quan, Long
Publication Year :
2019

Abstract

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that jointly optimizes the relative pose and target image depth has attracted the attention of the community. Previous works rely on the photometric error generated from depths and poses between adjacent frames, which contains large systematic error under realistic scenes due to reflective surfaces and occlusions. In this paper, we bridge the gap between geometric loss and photometric loss by introducing the matching loss constrained by epipolar geometry in a self-supervised framework. Evaluated on the KITTI dataset, our method outperforms the state-of-the-art unsupervised ego-motion estimation methods by a large margin. The code and data are available at https://github.com/hlzz/DeepMatchVO.<br />Comment: Accepted by ICRA 2019

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1902.09103
Document Type :
Working Paper