Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

TL;DR

This paper introduces a novel self-supervised ego-motion estimation method that combines geometric matching loss with photometric loss, significantly improving accuracy over existing approaches in realistic scenes.

Contribution

It proposes integrating epipolar geometry-based matching loss into self-supervised learning for ego-motion estimation, addressing limitations of photometric error under challenging conditions.

Findings

Outperforms state-of-the-art unsupervised methods on KITTI dataset

Effectively handles reflective surfaces and occlusions

Achieves significant accuracy improvements

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.