Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
This addresses a key bottleneck in visual odometry and SLAM for robotics and autonomous vehicles by improving accuracy in realistic scenes, though it is incremental as it builds on existing self-supervised frameworks.
The paper tackles the problem of inaccurate relative pose estimation in visual odometry and SLAM due to photometric errors from reflective surfaces and occlusions, by introducing a matching loss constrained by epipolar geometry in a self-supervised framework, resulting in outperforming state-of-the-art unsupervised ego-motion estimation methods by a large margin on the KITTI dataset.
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.