English

Two Stream Networks for Self-Supervised Ego-Motion Estimation

Computer Vision and Pattern Recognition 2019-11-20 v3 Image and Video Processing

Abstract

Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel self-supervised two-stream network using RGB and inferred depth information for accurate visual odometry. In addition, we introduce a sparsity-inducing data augmentation policy for ego-motion learning that effectively regularizes the pose network to enable stronger generalization performance. As a result, we show that our proposed two-stream pose network achieves state-of-the-art results among learning-based methods on the KITTI odometry benchmark, and is especially suited for self-supervision at scale. Our experiments on a large-scale urban driving dataset of 1 million frames indicate that the performance of our proposed architecture does indeed scale progressively with more data.

Keywords

Cite

@article{arxiv.1910.01764,
  title  = {Two Stream Networks for Self-Supervised Ego-Motion Estimation},
  author = {Rares Ambrus and Vitor Guizilini and Jie Li and Sudeep Pillai and Adrien Gaidon},
  journal= {arXiv preprint arXiv:1910.01764},
  year   = {2019}
}

Comments

Conference on Robot Learning (CoRL 2019)

R2 v1 2026-06-23T11:34:18.341Z